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

    Neuronpedia

    INDEX
    Explanations

    code and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üst
    0.82
    jacobian
    0.81
    觑
    0.80
    fabs
    0.79
    cede
    0.78
     തിരഞ്ഞെടു
    0.78
    ülő
    0.78
     ziff
    0.77
    printf
    0.77
     escolha
    0.76
    POSITIVE LOGITS
     &&
    0.85
     ===
    0.79
     ||
    0.79
     !==
    0.75
     Brain
    0.72
    &&(
    0.72
    ?'
    0.71
    &&
    0.71
     Gaz
    0.69
     đa
    0.68
    Act Density 0.081%

    No Known Activations