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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fad
    -0.07
     nw
    -0.07
     переп
    -0.07
     Clarkson
    -0.07
    stop
    -0.06
    _Param
    -0.06
     пат
    -0.06
     어머니
    -0.06
     Canterbury
    -0.06
    .SimpleDateFormat
    -0.06
    POSITIVE LOGITS
    ewhat
    0.08
     Retirement
    0.07
    Assigned
    0.07
     synt
    0.07
    ricane
    0.06
    clinical
    0.06
    ··
    0.06
    -*
    0.06
    UU
    0.06
     assigning
    0.06
    Act Density 0.047%

    No Known Activations