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

    Neuronpedia

    INDEX
    Explanations

    Russian text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Accessible
    -0.08
     Accessible
    -0.08
     Accessibility
    -0.08
     Winning
    -0.07
    _visible
    -0.07
     Responsibility
    -0.07
    �
    -0.07
    NSNotification
    -0.07
    Visible
    -0.07
    Winning
    -0.07
    POSITIVE LOGITS
     acc
    0.24
     Acc
    0.23
    Acc
    0.22
     доступ
    0.20
     hozzá
    0.19
    acc
    0.19
    'acc
    0.19
     অ্য
    0.18
    ’acc
    0.18
    (acc
    0.18
    Act Density 0.020%

    No Known Activations