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

    Neuronpedia

    INDEX
    Explanations

    believe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ｗ
    -0.08
     expiry
    -0.08
     supernatural
    -0.07
     Definitions
    -0.07
     warns
    -0.07
    難しい
    -0.07
     retro
    -0.07
     ontology
    -0.07
     absurd
    -0.06
    .fillStyle
    -0.06
    POSITIVE LOGITS
     К
    0.07
    =username
    0.07
     Bucket
    0.07
    otten
    0.07
     Lie
    0.06
    iteit
    0.06
    =length
    0.06
    .Group
    0.06
    上年同期
    0.06
     XCTestCase
    0.06
    Act Density 0.053%

    No Known Activations