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

    Neuronpedia

    INDEX
    Explanations

    panel discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.11
    I
    1.10
    S
    1.08
    i
    1.04
    5
    1.03
    L
    1.02
    -
    0.95
    .
    0.93
    2
    0.92
    6
    0.91
    POSITIVE LOGITS
    rijke
    0.99
     تین
    0.98
    pane
    0.95
     пане
    0.93
    cą
    0.91
     панели
    0.88
    ҷи
    0.88
     ойной
    0.87
     PANEL
    0.85
    cü
    0.85
    Act Density 0.005%

    No Known Activations