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

    Neuronpedia

    INDEX
    Explanations

    about to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pag
    -0.07
     transparency
    -0.07
     цьому
    -0.06
     Fault
    -0.06
    ость
    -0.06
     Jahre
    -0.06
     santa
    -0.06
     Lac
    -0.06
     Lav
    -0.06
    .userName
    -0.06
    POSITIVE LOGITS
    _ASSUME
    0.07
    enan
    0.07
     instantiation
    0.06
    ichick
    0.06
    ofile
    0.06
    ;↵↵↵↵↵
    0.06
    .Collapsed
    0.06
    тор
    0.06
    _TEM
    0.06
    quate
    0.06
    Act Density 0.016%

    No Known Activations