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

    Neuronpedia

    INDEX
    Explanations

    names and sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     owl
    -0.07
     tropical
    -0.07
     opting
    -0.07
     lo
    -0.06
     stress
    -0.06
     ");
    -0.06
     walk
    -0.06
    *.
    -0.06
    ived
    -0.06
     Sticky
    -0.06
    POSITIVE LOGITS
    .Dir
    0.07
    ереж
    0.07
     harass
    0.07
     �
    0.06
    توان
    0.06
    taboola
    0.06
     allele
    0.06
     Propel
    0.06
    بيرة
    0.06
    .getLine
    0.06
    Act Density 0.003%

    No Known Activations