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

    Neuronpedia

    INDEX
    Explanations

    Correcting text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Initial
    -0.07
    pleasant
    -0.07
     proteins
    -0.07
    �
    -0.07
     pleasant
    -0.06
    िड
    -0.06
     інтерес
    -0.06
     Glouce
    -0.06
    ้องพ
    -0.06
    _delta
    -0.06
    POSITIVE LOGITS
    Router
    0.06
     newArr
    0.06
    ٩
    0.06
     lashes
    0.06
     tmpl
    0.06
     simply
    0.06
    ////↵
    0.06
    [value
    0.06
     racket
    0.06
    +↵↵
    0.06
    Act Density 0.031%

    No Known Activations