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

    Neuronpedia

    INDEX
    Explanations

    rules and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avoro
    0.40
     nearly
    0.40
    ⁢</
    0.39
     زمانی
    0.38
    IJ
    0.38
    গম
    0.37
     அதே
    0.37
    letto
    0.37
    gação
    0.36
    გუ
    0.36
    POSITIVE LOGITS
     Rule
    0.91
    Rule
    0.82
     rule
    0.78
     RULE
    0.75
     regla
    0.70
    RULE
    0.66
    rule
    0.63
     règle
    0.62
    ForRule
    0.61
     रूल
    0.60
    Act Density 0.001%

    No Known Activations