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

    Neuronpedia

    INDEX
    Explanations

    genetic mutations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shaft
    -0.07
     persec
    -0.06
     mh
    -0.06
     overcoming
    -0.06
     Aş
    -0.06
    (R
    -0.06
     strat
    -0.06
     PLA
    -0.06
    化
    -0.06
    耶
    -0.06
    POSITIVE LOGITS
    remely
    0.07
    .gwt
    0.07
     txn
    0.07
    .Mapping
    0.07
    /configuration
    0.07
     underwater
    0.06
    _COLORS
    0.06
    _mini
    0.06
     громад
    0.06
     recycled
    0.06
    Act Density 0.009%

    No Known Activations