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

    Neuronpedia

    INDEX
    Explanations

    Independent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dx
    0.38
    nosis
    0.38
    ytic
    0.37
    drig
    0.36
    禄
    0.35
    razio
    0.35
     muda
    0.34
    ellular
    0.34
     rischi
    0.34
     نکن
    0.34
    POSITIVE LOGITS
     Independent
    0.64
    Independent
    0.58
     Independ
    0.57
     independ
    0.57
    independent
    0.55
     independent
    0.55
     Independence
    0.53
     independence
    0.52
     independents
    0.51
    independence
    0.49
    Act Density 0.003%

    No Known Activations