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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CircularProgress
    -0.07
     inher
    -0.07
    ultan
    -0.06
    मत
    -0.06
     lush
    -0.06
    imid
    -0.06
    _DIM
    -0.06
    .UndefOr
    -0.06
    _Font
    -0.06
    .Of
    -0.06
    POSITIVE LOGITS
     allege
    0.07
    (skill
    0.06
     stay
    0.06
     promising
    0.06
     expectations
    0.06
     excludes
    0.06
     Yugoslavia
    0.06
    �
    0.06
     улуч
    0.06
    asury
    0.06
    Act Density 0.000%

    No Known Activations