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

    Neuronpedia

    INDEX
    Explanations

    ized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kla
    -0.07
     summer
    -0.07
     NB
    -0.06
    cts
    -0.06
     evolution
    -0.06
     progresses
    -0.06
     sea
    -0.06
     polar
    -0.06
    Objects
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .Handled
    0.07
     فرانسه
    0.06
     userinfo
    0.06
    атков
    0.06
    }_
    0.06
    _GENERIC
    0.06
    ْح
    0.06
    براير
    0.06
    GRADE
    0.06
    -нибудь
    0.06
    Act Density 0.008%

    No Known Activations