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

    Neuronpedia

    INDEX
    Explanations

    history snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    voy
    -0.06
     hepat
    -0.06
     첨부파일
    -0.06
     yine
    -0.06
    _IDLE
    -0.06
     μια
    -0.06
     sent
    -0.06
    ادي
    -0.06
    postalcode
    -0.05
    超
    -0.05
    POSITIVE LOGITS
    .Company
    0.07
    _analysis
    0.07
    izabeth
    0.07
     Rap
    0.06
    (Vec
    0.06
     romantic
    0.06
     Charlotte
    0.06
     Bliss
    0.06
     sill
    0.06
    .Publish
    0.06
    Act Density 0.011%

    No Known Activations