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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Massachusetts
    -0.06
    993
    -0.06
    Positions
    -0.06
     Tur
    -0.06
    _index
    -0.06
    Actually
    -0.06
     blindness
    -0.06
     sympath
    -0.06
     extraction
    -0.06
    _ext
    -0.06
    POSITIVE LOGITS
    (ns
    0.07
    .masks
    0.07
    (id
    0.07
    _fid
    0.06
     blender
    0.06
    (gulp
    0.06
     caut
    0.06
     korum
    0.06
     бит
    0.06
    uyệt
    0.06
    Act Density 0.202%

    No Known Activations