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

    Neuronpedia

    INDEX
    Explanations

    keyloggers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndroidResource
    0.71
    桕
    0.68
     상수
    0.68
     Schlüssel
    0.67
     binatang
    0.67
     astronomy
    0.67
    ład
    0.67
    ="..."
    0.67
     getKey
    0.67
     KEYS
    0.66
    POSITIVE LOGITS
    ÇÃO
    0.82
    ção
    0.79
     चौहान
    0.78
     Lopez
    0.75
    Bowl
    0.74
     করানো
    0.72
    قبال
    0.72
    cher
    0.72
    nesi
    0.72
    Lopez
    0.72
    Act Density 0.005%

    No Known Activations