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

    Neuronpedia

    INDEX
    Explanations

    releases or specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وف
    0.54
    ٦
    0.50
    皮革
    0.50
    疑惑
    0.48
    プレ
    0.48
     हौ
    0.48
    逸
    0.48
    薪
    0.47
    のような
    0.46
    水素
    0.46
    POSITIVE LOGITS
    ão
    0.53
    n
    0.48
    im
    0.47
    odos
    0.46
    ubar
    0.46
    Gen
    0.46
    rot
    0.46
    isy
    0.46
    amento
    0.45
    genos
    0.44
    Act Density 0.001%

    No Known Activations