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

    Neuronpedia

    INDEX
    Explanations

    bullet points and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ankles
    0.49
    เส้น
    0.47
    裙
    0.46
    permalink
    0.45
     immunoprec
    0.45
     elegantes
    0.44
     mientras
    0.44
    headphones
    0.44
     penjelasan
    0.44
    yarn
    0.43
    POSITIVE LOGITS
     Kas
    0.47
     Roy
    0.46
     to
    0.45
     Jacob
    0.44
     legacy
    0.44
     Rot
    0.43
     Typ
    0.42
    酭
    0.42
     Edwin
    0.42
     ROY
    0.42
    Act Density 0.003%

    No Known Activations