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

    Neuronpedia

    INDEX
    Explanations

    dont

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     may
    -0.07
    >()
    -0.07
     laundry
    -0.06
     coins
    -0.06
    idine
    -0.06
    Label
    -0.06
     samozřejmě
    -0.06
     configuration
    -0.06
    Exception
    -0.06
     resistance
    -0.06
    POSITIVE LOGITS
     徒
    0.08
     whats
    0.07
    __,__
    0.06
     doesnt
    0.06
    thern
    0.06
    _CLR
    0.06
    frica
    0.06
    kb
    0.06
    -topic
    0.06
     爱
    0.06
    Act Density 0.029%

    No Known Activations