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

    Neuronpedia

    INDEX
    Explanations

    `const` declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    н
    2.34
    ला
    2.28
    ৮
    2.27
    𝒐
    2.16
    ли
    2.13
    𝒂
    2.09
    ı
    2.08
    ை
    1.98
    𝒍
    1.89
    𝒖
    1.89
    POSITIVE LOGITS
    s
    2.33
    től
    2.27
    sites
    2.23
    tól
    2.16
    smanship
    2.06
    sons
    2.06
    soever
    1.95
    rays
    1.94
    scapes
    1.94
    sG
    1.93
    Act Density 0.016%

    No Known Activations