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

    Neuronpedia

    INDEX
    Explanations

    soul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     educated
    -0.07
    levard
    -0.07
     isten
    -0.06
    hattan
    -0.06
    iado
    -0.06
    KEN
    -0.06
    erase
    -0.06
    _POS
    -0.06
    iken
    -0.06
     snacks
    -0.06
    POSITIVE LOGITS
     soul
    0.17
     Soul
    0.16
     souls
    0.11
     Souls
    0.09
    Sou
    0.08
    uti
    0.08
     Accountability
    0.08
     Alma
    0.07
    魂
    0.07
    205
    0.07
    Act Density 0.005%

    No Known Activations