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

    Neuronpedia

    INDEX
    Explanations

    projects, specifications, stories, brains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.49
    ↵
    0.45
    on
    0.44
    py
    0.44
    up
    0.43
    Q
    0.42
    izio
    0.42
    Flow
    0.40
    он
    0.40
    k
    0.40
    POSITIVE LOGITS
    थोरो
    0.53
    starcore
    0.49
    اردوش
    0.47
    '><
    0.47
     cryptographic
    0.47
    '];?>
    0.47
    ᐳ
    0.46
    loadNpm
    0.46
    MktCap
    0.46
    讣
    0.46
    Act Density 0.000%

    No Known Activations