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

    Neuronpedia

    INDEX
    Explanations

    from and of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Number
    -0.07
     loops
    -0.07
    _GL
    -0.07
    _de
    -0.07
    CardContent
    -0.06
    _numbers
    -0.06
    .backend
    -0.06
     stellen
    -0.06
    �
    -0.06
    Ticks
    -0.06
    POSITIVE LOGITS
     controversies
    0.07
    ें,
    0.07
     homosexual
    0.06
     reach
    0.06
     оцен
    0.06
     ฟร
    0.06
    ैं।↵↵
    0.06
     equivalence
    0.06
    การส
    0.06
     reviewers
    0.06
    Act Density 0.007%

    No Known Activations