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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мит
    -0.07
    _vocab
    -0.07
     것이다
    -0.07
     кількість
    -0.07
    _require
    -0.07
    <typeof
    -0.07
    edef
    -0.07
    -Dec
    -0.06
    Bs
    -0.06
    _patches
    -0.06
    POSITIVE LOGITS
    THIS
    0.06
     galaxy
    0.06
     đứng
    0.06
     withstand
    0.06
     spiders
    0.06
    alarından
    0.06
    ože
    0.06
     sho
    0.06
     deck
    0.06
     odpowied
    0.06
    Act Density 0.007%

    No Known Activations