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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     override
    -0.07
    .scal
    -0.06
    _Enc
    -0.06
    Automatic
    -0.06
    .leave
    -0.06
     expres
    -0.06
     활동
    -0.06
     Bart
    -0.06
     Maven
    -0.06
    _Name
    -0.06
    POSITIVE LOGITS
    iores
    0.07
     addObject
    0.07
    maries
    0.06
     hitch
    0.06
    ights
    0.06
     highs
    0.06
    ientes
    0.06
     altı
    0.06
    anos
    0.06
    Sunday
    0.06
    Act Density 0.000%

    No Known Activations