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

    Neuronpedia

    INDEX
    Explanations

    importing axios library

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.94
    ską
    0.88
    ں
    0.81
    нтов
    0.80
    ون
    0.80
    σης
    0.79
    skih
    0.78
    ses
    0.77
    DUCTION
    0.74
    symplectic
    0.73
    POSITIVE LOGITS
    l
    1.02
    ü
    0.92
    ı
    0.85
    /
    0.84
    ă
    0.82
     Axios
    0.75
    2
    0.75
     Instance
    0.75
     axios
    0.74
    מ
    0.74
    Act Density 0.000%

    No Known Activations