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

    Neuronpedia

    INDEX
    Explanations

    double-check verification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inals
    0.76
    லின்
    0.72
    lettes
    0.71
    ᾧ
    0.71
    ⥤
    0.67
    லும்
    0.67
     McGu
    0.66
    encia
    0.66
     прадстаў
    0.66
     ఆధార
    0.66
    POSITIVE LOGITS
     check
    1.05
    check
    0.97
     Check
    0.92
    examine
    0.87
    Check
    0.85
    チェック
    0.82
     Checks
    0.79
     nevertheless
    0.79
     examine
    0.78
     Examine
    0.77
    Act Density 0.003%

    No Known Activations