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
    (月
    -0.07
     tether
    -0.06
     molt
    -0.06
     therm
    -0.06
     u
    -0.06
     Prediction
    -0.06
    arian
    -0.06
     millones
    -0.06
     difficile
    -0.06
    Verifier
    -0.06
    POSITIVE LOGITS
    Here
    0.06
    -method
    0.06
    態
    0.06
    =img
    0.06
     @"";↵
    0.06
    .chart
    0.06
    meal
    0.06
     guest
    0.06
    ména
    0.06
    ूड
    0.06
    Act Density 0.015%

    No Known Activations