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

    Neuronpedia

    INDEX
    Explanations

    One

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gaz
    -0.07
     worse
    -0.06
    рон
    -0.06
     gam
    -0.06
     Böylece
    -0.06
    cept
    -0.06
     cue
    -0.06
     ort
    -0.06
    тери
    -0.06
    onaut
    -0.06
    POSITIVE LOGITS
    ,std
    0.07
    ','".$
    0.07
    ,key
    0.07
    ated
    0.06
     Booker
    0.06
    込み
    0.06
    =create
    0.06
    }/#{
    0.06
     अपन
    0.06
     instructor
    0.06
    Act Density 0.000%

    No Known Activations