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

    Neuronpedia

    INDEX
    Explanations

    remove

    np_max-act · gemini-2.0-flash

    The neuron fires on terms that describe modifying a structure—especially adding or removing elements (e.g. “adding,” “removing,” “columns,” “properties”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    },
↵
    -0.08
     OTHERWISE
    -0.07
     بعد
    -0.07
     FIX
    -0.07
    .Lock
    -0.07
     },↵↵↵
    -0.07
     hexatrigesimal
    -0.07
     acids
    -0.06
    ��
    -0.06
    Titan
    -0.06
    POSITIVE LOGITS
    activ
    0.08
     lone
    0.06
     Mystery
    0.06
    etine
    0.06
    ::$
    0.06
    ूज
    0.06
    elop
    0.06
     Jur
    0.06
    -status
    0.06
    fant
    0.06
    Act Density 0.010%

    No Known Activations