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

    Neuronpedia

    INDEX
    Explanations

    fuse box and parse errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ене
    0.44
     Verfü
    0.43
    Playing
    0.42
    )}$
    0.42
    ولي
    0.42
    .*;
    0.40
     Verbrauch
    0.40
    鼍
    0.40
     Gesundheit
    0.40
    ጀም
    0.40
    POSITIVE LOGITS
    pple
    0.53
     ме
    0.47
     utilisent
    0.46
    nać
    0.46
     ін
    0.45
     supersymmetric
    0.45
     способом
    0.45
    aspid
    0.44
     uso
    0.44
    intell
    0.44
    Act Density 0.000%

    No Known Activations