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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声音
    -0.07
    _checkpoint
    -0.07
    _To
    -0.06
     loop
    -0.06
     ESP
    -0.06
     згад
    -0.06
    .Bl
    -0.06
     Cumhuriyeti
    -0.06
     Kohana
    -0.06
    dlg
    -0.06
    POSITIVE LOGITS
    otle
    0.07
     Registered
    0.07
     ücret
    0.06
    lemen
    0.06
    most
    0.06
    allery
    0.06
    ilities
    0.06
     Vanity
    0.06
     Register
    0.06
     tướng
    0.06
    Act Density 0.079%

    No Known Activations