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

    Neuronpedia

    INDEX
    Explanations

    July

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ℛ
    -0.08
     signify
    -0.07
     shot
    -0.07
     Sym
    -0.07
     Inch
    -0.07
     Rus
    -0.07
    jt
    -0.07
    执教
    -0.06
    信誉
    -0.06
     khỏi
    -0.06
    POSITIVE LOGITS
     wealthiest
    0.07
     avoidance
    0.07
    行业协会
    0.07
    -responsive
    0.06
    .headers
    0.06
    いません
    0.06
    /hooks
    0.06
    predictions
    0.06
     bakeca
    0.06
    ALES
    0.06
    Act Density 0.003%

    No Known Activations