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

    Neuronpedia

    INDEX
    Explanations

    detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pesa
    0.46
    읊
    0.46
     eşit
    0.45
     dham
    0.45
     Buhari
    0.45
     города
    0.44
     ночь
    0.44
     власть
    0.44
     Yani
    0.44
     слово
    0.44
    POSITIVE LOGITS
    detect
    0.53
    micro
    0.51
    detection
    0.50
    branch
    0.49
     detection
    0.49
     detects
    0.48
     detected
    0.46
    detector
    0.46
     detector
    0.46
    motor
    0.46
    Act Density 0.003%

    No Known Activations