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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron detects decimal-number tokens (floating‐point numeric answers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    apiro
    -0.07
    政
    -0.06
    -danger
    -0.06
     tq
    -0.06
    iple
    -0.06
    .CENTER
    -0.05
    _stack
    -0.05
    (rc
    -0.05
    vě
    -0.05
    OBJECT
    -0.05
    POSITIVE LOGITS
     deeper
    0.07
    iculos
    0.07
    _Info
    0.07
     insulation
    0.06
     Ελλάδα
    0.06
    vably
    0.06
     horror
    0.06
     listened
    0.06
     multi
    0.06
    oufl
    0.06
    Act Density 0.001%

    No Known Activations