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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ชม
    -0.07
     Hayden
    -0.07
     terminator
    -0.07
     overly
    -0.06
    に
    -0.06
    Load
    -0.06
     unimagin
    -0.06
    ffiti
    -0.06
    茂
    -0.06
     코
    -0.06
    POSITIVE LOGITS
    ิจ
    0.07
     errone
    0.07
     přibliž
    0.06
     withdrawal
    0.06
    avatar
    0.06
    rics
    0.06
    (src
    0.06
    DR
    0.06
    ль
    0.06
    dni
    0.06
    Act Density 0.002%

    No Known Activations