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

    Neuronpedia

    INDEX
    Explanations

    express javascript code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expressed
    0.47
    Year
    0.44
     Year
    0.43
     Năm
    0.42
    百年
    0.39
     Centuries
    0.38
    expressed
    0.38
     Passing
    0.36
     guerre
    0.36
     esprim
    0.36
    POSITIVE LOGITS
    ount
    0.43
     coffee
    0.43
     roses
    0.42
     priv
    0.40
     asleep
    0.40
     coffees
    0.40
    뚠
    0.40
     reacting
    0.39
    錆
    0.39
     locating
    0.39
    Act Density 0.001%

    No Known Activations