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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    远
    -0.07
     partly
    -0.07
     greatly
    -0.07
     zů
    -0.07
     sufficient
    -0.06
     seldom
    -0.06
    ाइल
    -0.06
    flux
    -0.06
     фінанс
    -0.06
    col
    -0.06
    POSITIVE LOGITS
     eve
    0.08
    ORIGINAL
    0.07
    valueOf
    0.07
    論
    0.06
    flutter
    0.06
    _Per
    0.06
    .ec
    0.06
    .parse
    0.06
     familial
    0.06
     LANGUAGE
    0.06
    Act Density 0.062%

    No Known Activations