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

    Neuronpedia

    INDEX
    Explanations

    California and associated contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     límites
    0.48
     حالة
    0.46
     carav
    0.44
     ওয়
    0.44
     verdes
    0.43
    çou
    0.43
     límite
    0.43
     zerstört
    0.42
    铒
    0.42
     courthouse
    0.42
    POSITIVE LOGITS
    '
    0.55
    isering
    0.49
    _
    0.48
    ingly
    0.47
    H
    0.44
    特性
    0.44
    は
    0.42
    筒
    0.42
    plication
    0.41
    錤
    0.41
    Act Density 0.001%

    No Known Activations