Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    demolition

    np_max-act · gemini-2.0-flash

    references to demolition and urban development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects references to demolishing or tearing down structures (e.g., “demolition,” “razed,” “wrecking ball,” “demolish”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .PreparedStatement
    -0.07
    successfully
    -0.07
    todos
    -0.07
    аче
    -0.06
     eagle
    -0.06
    غة
    -0.06
     unprotected
    -0.06
     PyObject
    -0.06
    ूप
    -0.06
    promise
    -0.06
    POSITIVE LOGITS
     demolition
    0.10
     demol
    0.08
    642
    0.07
    ■■
    0.07
     demolished
    0.07
     β
    0.06
    lož
    0.06
    731
    0.06
    μα
    0.06
    εχ
    0.06
    Act Density 0.005%

    No Known Activations