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

    Neuronpedia

    INDEX
    Explanations

    rule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diseñador
    -0.07
    ящ
    -0.06
    ónica
    -0.06
    Spawn
    -0.06
    346
    -0.06
    optimizer
    -0.06
    osaurs
    -0.06
    athy
    -0.06
     Tobias
    -0.06
    /kernel
    -0.06
    POSITIVE LOGITS
     rule
    0.13
     rules
    0.12
    Rule
    0.11
     Rule
    0.11
     RULE
    0.09
     Rules
    0.09
     правил
    0.08
    rules
    0.08
    规
    0.08
    .rule
    0.08
    Act Density 0.027%

    No Known Activations