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

    Neuronpedia

    INDEX
    Explanations

    appearance expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    丐
    0.50
     eradic
    0.48
     anecd
    0.47
     alveolar
    0.47
     Ehrlich
    0.47
     Echin
    0.47
    krét
    0.45
     yelling
    0.45
     shady
    0.44
    𝘇
    0.44
    POSITIVE LOGITS
    शिला
    0.43
    Fuse
    0.43
    फल
    0.42
    ARI
    0.42
    getQuery
    0.41
    Lily
    0.40
    成为
    0.40
    OSS
    0.40
    แมนเชสเตอร์ซิตี
    0.40
    Dom
    0.39
    Act Density 0.000%

    No Known Activations