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

    Neuronpedia

    INDEX
    Explanations

    generic animal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.12
    y
    1.02
    temperature
    0.84
     нача
    0.79
    time
    0.77
    terminal
    0.77
    table
    0.76
     потреб
    0.76
    י
    0.75
    market
    0.74
    POSITIVE LOGITS
     Multin
    0.79
     COUNT
    0.77
     NUM
    0.76
     MTN
    0.75
     Frozen
    0.74
     EPIC
    0.74
     rares
    0.73
     SCALE
    0.72
     CONTAIN
    0.71
     Epic
    0.71
    Act Density 0.011%

    No Known Activations