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

    Neuronpedia

    INDEX
    Explanations

    deferred until, million, training cutting-edge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    наче
    0.89
     olhando
    0.86
    Ծ
    0.84
    IZONTAL
    0.78
    zag
    0.77
     Così
    0.76
    neze
    0.76
    زمانہ
    0.76
    ክ
    0.76
     aclar
    0.75
    POSITIVE LOGITS
    uding
    0.87
    senha
    0.77
    大规模
    0.75
    rukt
    0.75
    于
    0.74
    綠
    0.74
    alit
    0.74
    로부터
    0.73
     ভেসে
    0.73
    вки
    0.73
    Act Density 0.000%

    No Known Activations