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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of “friend” or “friends” in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    [layer
    -0.07
     PP
    -0.07
     *
    -0.06
     Sandy
    -0.06
     Diagram
    -0.06
     Tabs
    -0.06
     réalis
    -0.06
     alignments
    -0.06
     Capitol
    -0.06
     Ax
    -0.06
    POSITIVE LOGITS
    .Connect
    0.06
    /report
    0.06
    ZW
    0.06
    _RECEIVED
    0.06
    #import
    0.06
     общ
    0.06
     grub
    0.06
     carga
    0.06
     무료
    0.06
     tzv
    0.06
    Act Density 0.017%

    No Known Activations