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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ा↵↵
    -0.06
    '>↵
    -0.06
    _version
    -0.06
     k
    -0.06
    lein
    -0.06
     purchase
    -0.06
    ูล
    -0.06
    ूम
    -0.06
    остей
    -0.06
    ForgeryToken
    -0.06
    POSITIVE LOGITS
    $template
    0.06
     тол
    0.06
    握
    0.06
     clash
    0.06
     піш
    0.06
     ';'
    0.06
    semb
    0.06
     hormonal
    0.06
     Ansi
    0.06
     ممن
    0.06
    Act Density 0.008%

    No Known Activations