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

    Neuronpedia

    INDEX
    Explanations

    short function words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,number
    -0.07
     dear
    -0.07
    mph
    -0.06
     preced
    -0.06
     pardon
    -0.06
     iken
    -0.06
     THANK
    -0.06
     also
    -0.06
     lecturer
    -0.06
     killings
    -0.06
    POSITIVE LOGITS
     перен
    0.07
    profession
    0.06
     mitochond
    0.06
     technicians
    0.06
    achinery
    0.06
    uras
    0.05
    rms
    0.05
     бет
    0.05
    Formatter
    0.05
     cadena
    0.05
    Act Density 0.037%

    No Known Activations