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

    Neuronpedia

    INDEX
    Explanations

    initializing code and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    1.36
    s
    1.27
     in
    1.22
    mu
    1.05
    お
    1.05
    的
    1.05
    も
    1.03
    $)$.
    1.02
    が
    1.02
    ます
    0.99
    POSITIVE LOGITS
    ت
    1.45
    ير
    1.35
    т
    1.27
    us
    1.20
    ো
    1.16
    ر
    1.09
    ే
    1.06
    ర్
    1.05
    ומי
    1.05
    ле
    1.03
    Act Density 0.079%

    No Known Activations