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

    Neuronpedia

    INDEX
    Explanations

    Report

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    2.13
     וע
    2.06
    na
    1.91
    س
    1.81
    ました
    1.78
    <0x80>
    1.76
    yyyyyyyy
    1.73
    ма
    1.70
    ﻭ
    1.70
    nd
    1.66
    POSITIVE LOGITS
    ли
    2.06
    alunos
    1.91
    ির
    1.80
    ać
    1.73
     strictement
    1.70
    ानंतर
    1.68
    و
    1.65
    zero
    1.63
    eau
    1.63
    ie
    1.61
    Act Density 0.088%

    No Known Activations