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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic Text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     racer
    -0.07
    w
    -0.07
    range
    -0.06
    ajor
    -0.06
    (candidate
    -0.06
     readers
    -0.06
    �
    -0.06
     strtotime
    -0.06
     fighter
    -0.06
     Predator
    -0.06
    POSITIVE LOGITS
    rawtypes
    0.07
    (sig
    0.07
    icemail
    0.06
     empathy
    0.06
    .FirstName
    0.06
     sealing
    0.06
    phthalm
    0.06
     //================================================================
    0.06
     guarda
    0.06
     аром
    0.06
    Act Density 0.003%

    No Known Activations