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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kosten
    -0.07
     prostitut
    -0.07
    )")↵↵
    -0.06
    omanip
    -0.06
    (topic
    -0.06
    !');↵
    -0.06
    ')"↵
    -0.06
    _suffix
    -0.06
     authDomain
    -0.06
     lä
    -0.06
    POSITIVE LOGITS
    очных
    0.08
    agged
    0.07
     него
    0.06
    痛
    0.06
    oS
    0.06
     scholar
    0.06
    CartItem
    0.06
     Parsons
    0.06
     arcade
    0.06
    ФЛ
    0.06
    Act Density 0.008%

    No Known Activations