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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reached
    0.51
    ZE
    0.50
    Reached
    0.50
    Isa
    0.49
     связи
    0.48
    ･
    0.47
    踏
    0.46
    reached
    0.46
    INSTANCE
    0.46
    系統
    0.45
    POSITIVE LOGITS
     remaining
    0.91
     나머지
    0.84
     remainder
    0.79
     restante
    0.78
    remaining
    0.73
     restantes
    0.71
     Remaining
    0.70
    remainder
    0.70
    Remaining
    0.66
     остав
    0.66
    Act Density 0.135%

    No Known Activations