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

    Neuronpedia

    INDEX
    Explanations

    ## section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    エンド
    0.37
    यान
    0.36
    喏
    0.36
    ವಾಗಿರುತ್ತದೆ
    0.33
     grouping
    0.33
    __);
    0.33
    ುದು
    0.33
    য়ো
    0.32
    各
    0.32
    hwnd
    0.32
    POSITIVE LOGITS
    </h2>
    0.82
    ##
    0.39
     '
    0.38
     ##
    0.38
     """
    0.37
    <h2>
    0.36
    </h1>
    0.36
    𝙫
    0.35
    </h3>
    0.35
    ")
    0.34
    Act Density 0.003%

    No Known Activations