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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;.
    -0.07
    多
    -0.07
     shining
    -0.06
    sav
    -0.06
     pork
    -0.06
    colour
    -0.06
    =".
    -0.06
     nal
    -0.06
     теп
    -0.06
    是一个
    -0.06
    POSITIVE LOGITS
    _commit
    0.07
    xfb
    0.06
     Adults
    0.06
     occupants
    0.06
     Humph
    0.06
     pagar
    0.06
     microbi
    0.06
    abort
    0.06
     defects
    0.06
     adults
    0.06
    Act Density 0.020%

    No Known Activations