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

    Neuronpedia

    INDEX
    Explanations

    China views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finalizing
    0.80
     पहुंचाया
    0.79
     affordability
    0.72
     confirming
    0.71
     VIII
    0.70
     crystallinity
    0.70
     PHD
    0.69
     Porta
    0.68
    ᵃ
    0.68
     affirmed
    0.68
    POSITIVE LOGITS
    jou
    0.83
    irl
    0.83
    ಋ
    0.82
    iais
    0.80
    pt
    0.79
    ış
    0.78
    iguous
    0.78
    jt
    0.77
     vrste
    0.76
    iskt
    0.75
    Act Density 0.008%

    No Known Activations