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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “How
    -0.07
    Aus
    -0.07
    PropertyParams
    -0.07
     twentieth
    -0.06
    (source
    -0.06
    Summary
    -0.06
     theres
    -0.06
     demographic
    -0.06
     makes
    -0.06
    руч
    -0.06
    POSITIVE LOGITS
    xFD
    0.08
    \Events
    0.07
     修
    0.07
     Cliente
    0.07
    ственных
    0.06
     signIn
    0.06
    .Collapsed
    0.06
     Kết
    0.06
     synchronous
    0.06
    typing
    0.06
    Act Density 0.000%

    No Known Activations