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

    Neuronpedia

    INDEX
    Explanations

    "nothing more"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.57
    CH
    0.54
    DE
    0.52
    )
    0.52
    _
    0.51
    ;
    0.51
    TE
    0.49
    r
    0.49
    ost
    0.48
     quelqu
    0.47
    POSITIVE LOGITS
    ية
    0.61
    ㄢ
    0.59
     turista
    0.58
    jeć
    0.55
     landings
    0.54
    ujjati
    0.54
     appease
    0.54
    вича
    0.52
    уса
    0.52
    ヤモンド
    0.52
    Act Density 0.002%

    No Known Activations