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

    Neuronpedia

    INDEX
    Explanations

    announcement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autopsy
    -0.07
     �
    -0.07
     Live
    -0.06
    "L
    -0.06
    moil
    -0.06
    _qual
    -0.06
     Hubbard
    -0.06
    Ahead
    -0.06
     Piano
    -0.06
     Aut
    -0.06
    POSITIVE LOGITS
    ющая
    0.07
    Traditional
    0.06
    renom
    0.06
    ��
    0.06
    まだ
    0.06
    ющей
    0.06
    ChangedEventArgs
    0.06
    никам
    0.06
    умент
    0.06
    ieur
    0.06
    Act Density 0.000%

    No Known Activations