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

    Neuronpedia

    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash

    The neuron fires on words that denote spatial relationships or distance (e.g. “remote,” “close,” “proximity,” “linking”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     compr
    -0.07
    (zip
    -0.07
    .Cond
    -0.07
    _PROD
    -0.07
     undef
    -0.07
     warrant
    -0.07
    AST
    -0.07
    _STANDARD
    -0.07
    ADIO
    -0.07
    ونت
    -0.07
    POSITIVE LOGITS
    عدد
    0.07
    ότητα
    0.07
    _edges
    0.06
     userDetails
    0.06
     sadece
    0.06
     Woj
    0.06
    value
    0.06
     возникает
    0.06
    Jvm
    0.06
     абсолютно
    0.06
    Act Density 0.181%

    No Known Activations