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

    Neuronpedia

    INDEX
    Explanations

    likely to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ({\
    0.43
    阉
    0.40
     시설
    0.39
     ((
    0.39
     Autodesk
    0.39
     संयंत्र
    0.38
    蹇
    0.38
    沔
    0.38
    시설
    0.38
     Determines
    0.38
    POSITIVE LOGITS
    DAV
    0.42
    Gre
    0.40
    Fab
    0.39
    *.
    0.37
     अली
    0.37
    แม
    0.37
     பு
    0.37
     shirts
    0.37
    Robin
    0.37
    akkhand
    0.36
    Act Density 0.000%

    No Known Activations