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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .o
    -0.07
    Sun
    -0.06
    ,*
    -0.06
    .not
    -0.06
    /not
    -0.06
    *N
    -0.06
     itemBuilder
    -0.06
     SharedPreferences
    -0.06
    _called
    -0.06
    stral
    -0.06
    POSITIVE LOGITS
     encouragement
    0.08
     Inspection
    0.07
     mesure
    0.07
     ventured
    0.06
     Ris
    0.06
     Talk
    0.06
     Oliveira
    0.06
     residual
    0.06
     مت
    0.06
    　　　　　　　　　　　
    0.06
    Act Density 0.003%

    No Known Activations