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

    Neuronpedia

    INDEX
    Explanations

    formatting/writing guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     હુમ
    -0.09
     breakthroughs
    -0.09
    _attack
    -0.09
    探索
    -0.09
     hostage
    -0.08
    <TResult
    -0.08
    Tunnel
    -0.08
     घाट
    -0.08
    attack
    -0.08
     overcoming
    -0.08
    POSITIVE LOGITS
     punctuation
    0.14
     formatting
    0.13
     Formatting
    0.12
    unctuation
    0.12
     standardized
    0.12
    Formatting
    0.12
    遵
    0.12
     etiquette
    0.11
    规范
    0.11
     precedence
    0.11
    Act Density 0.018%

    No Known Activations