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

    Neuronpedia

    INDEX
    Explanations

    Palo Alto Networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nan
    0.80
     “‘
    0.76
    nas
    0.76
    на
    0.75
    ná
    0.74
    na
    0.73
    nou
    0.73
    awas
    0.71
     Section
    0.71
    ران
    0.71
    POSITIVE LOGITS
    较高的
    1.02
    𝗬
    1.02
    acariy
    0.99
     лигасы
    0.98
     tyrann
    0.96
    较大的
    0.93
     gobernador
    0.93
    鉭
    0.93
     coseno
    0.92
    SSL
    0.91
    Act Density 0.001%

    No Known Activations