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

    Neuronpedia

    INDEX
    Explanations

    TYPE or reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kipun
    1.08
    stuffs
    1.00
    akaranam
    0.94
    에도
    0.93
    збеки
    0.93
     accred
    0.92
    0.92
    𒅀
    0.91
    kprop
    0.90
     මිල
    0.89
    POSITIVE LOGITS
    em
    0.93
    ят
    0.82
    ↵
    0.78
    I
    0.78
    ю
    0.77
    een
    0.74
    d
    0.73
    ent
    0.72
    ่
    0.71
    at
    0.71
    Act Density 0.000%

    No Known Activations