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

    Neuronpedia

    INDEX
    Explanations

    Technical research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     решил
    -0.07
     lesbian
    -0.07
     namoro
    -0.07
     startActivityForResult
    -0.07
     adım
    -0.07
     Vick
    -0.07
     псих
    -0.07
     gelişme
    -0.07
    gunta
    -0.07
     במקרה
    -0.07
    POSITIVE LOGITS
    [__
    0.07
    almost
    0.07
     Yet
    0.06
    pl
    0.06
    plement
    0.06
     Les
    0.06
     windows
    0.06
    כושר
    0.06
    times
    0.06
    负
    0.06
    Act Density 0.091%

    No Known Activations