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

    Neuronpedia

    INDEX
    Explanations

    Foreign characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cialis
    -0.07
    ሊ
    -0.07
    ademic
    -0.07
    猊
    -0.07
    rij
    -0.07
    誠
    -0.07
    bff
    -0.07
     sincerity
    -0.07
     Iraq
    -0.07
     Sabb
    -0.07
    POSITIVE LOGITS
    urls
    0.07
    는
    0.07
     puts
    0.07
    (Display
    0.07
    _ring
    0.06
     threading
    0.06
    "log
    0.06
     beforehand
    0.06
     veut
    0.06
    localized
    0.06
    Act Density 0.022%

    No Known Activations