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

    Neuronpedia

    INDEX
    Explanations

    wind loads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reihe
    0.38
    будь
    0.37
    䪲
    0.37
     Siegfried
    0.37
    ιασ
    0.37
    王的
    0.37
     grinding
    0.36
     rigid
    0.36
     Sulf
    0.36
     mostra
    0.36
    POSITIVE LOGITS
     Character
    0.52
     character
    0.49
    Character
    0.48
    setCharacter
    0.45
    character
    0.43
    rewrite
    0.42
     charakter
    0.39
    Tiny
    0.38
     rewrite
    0.38
    tiny
    0.37
    Act Density 0.000%

    No Known Activations