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

    Neuronpedia

    INDEX
    Explanations

    Rounds numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hun
    -0.07
    ;}↵↵
    -0.07
     para
    -0.06
     깨
    -0.06
     succeeded
    -0.06
     계약
    -0.06
     Öl
    -0.06
     literal
    -0.06
    .COL
    -0.06
     backward
    -0.06
    POSITIVE LOGITS
    leri
    0.06
    opsis
    0.06
    üph
    0.06
    麗
    0.06
    _gem
    0.06
    _stock
    0.06
     laughs
    0.06
    oto
    0.06
    _approved
    0.06
     photograph
    0.06
    Act Density 0.020%

    No Known Activations