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

    Neuronpedia

    INDEX
    Explanations

    varied explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    1.67
    s
    1.66
    ের
    1.49
    en
    1.46
    ió
    1.45
    sab
    1.41
    sb
    1.40
    ند
    1.34
    mesh
    1.34
    ે
    1.33
    POSITIVE LOGITS
     Prelude
    1.29
     Sailing
    1.26
    טר
    1.25
     Gewalt
    1.25
    ರ್ಚ
    1.25
    ق
    1.25
     Fundamentals
    1.24
     Revised
    1.24
    ジナル
    1.23
     merupakan
    1.21
    Act Density 0.000%

    No Known Activations