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

    Neuronpedia

    INDEX
    Explanations

    path traversal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.89
     Σ
    0.85
     coleta
    0.82
     movimentos
    0.80
     צ
    0.78
     що
    0.78
    га
    0.77
     шрифт
    0.77
     courte
    0.77
     cocina
    0.76
    POSITIVE LOGITS
    t
    1.00
    r
    1.00
    ции
    0.84
    <0x0D>
    0.80
    ant
    0.79
    रा
    0.77
    ../../
    0.77
    த்தது
    0.77
    ('../
    0.76
    rj
    0.75
    Act Density 0.002%

    No Known Activations