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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esi
    -0.08
    ьи
    -0.07
    нюю
    -0.07
     ("/
    -0.07
    verification
    -0.06
    任何
    -0.06
     başarı
    -0.06
    톤
    -0.06
     dục
    -0.06
     Fiction
    -0.06
    POSITIVE LOGITS
     promised
    0.07
     friend
    0.07
     distrib
    0.07
     Sab
    0.07
     holiday
    0.07
    _patches
    0.06
    _mA
    0.06
    ２０
    0.06
    .Tab
    0.06
    _RG
    0.06
    Act Density 0.002%

    No Known Activations