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

    Neuronpedia

    INDEX
    Explanations

    cheaper

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ap
    0.82
    ith
    0.74
     ap
    0.74
     Mat
    0.72
     py
    0.72
    ิก
    0.70
     Ná
    0.70
    ан
    0.69
     Quad
    0.68
     app
    0.68
    POSITIVE LOGITS
    vres
    0.88
    精彩
    0.87
    轨迹
    0.82
    ﻱ
    0.81
    ್
    0.81
    osphäre
    0.80
     verlieren
    0.79
    ว์
    0.77
    ්‍
    0.77
     virulence
    0.76
    Act Density 0.000%

    No Known Activations