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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.07
     ส
    -0.07
    ،
    -0.06
     ";
    -0.06
    f
    -0.06
    raf
    -0.06
     Ге
    -0.06
     Chop
    -0.06
    ähl
    -0.06
     encourages
    -0.06
    POSITIVE LOGITS
    -Disposition
    0.07
    _Common
    0.07
     kullanıl
    0.06
     축
    0.06
    _SEP
    0.06
    TRANS
    0.06
    xca
    0.06
    ilinx
    0.06
    _Stream
    0.06
    ствен
    0.06
    Act Density 0.001%

    No Known Activations