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

    Neuronpedia

    INDEX
    Explanations

    process.env

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ará
    0.73
     This
    0.72
     режисс
    0.69
    톈
    0.69
    清新
    0.67
     CarPlay
    0.66
     HIPAA
    0.65
    arı
    0.64
    министра
    0.64
    ladesh
    0.63
    POSITIVE LOGITS
    ز
    0.89
    IC
    0.88
    Z
    0.85
    ات
    0.84
    IN
    0.75
    ES
    0.74
    EN
    0.71
    AC
    0.71
    0
    0.71
    ED
    0.69
    Act Density 0.003%

    No Known Activations