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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ###↵
    -0.06
     直
    -0.06
    τικός
    -0.06
     alanda
    -0.06
    779
    -0.06
     Mey
    -0.06
    _sphere
    -0.06
    ..."↵↵
    -0.06
    ولد
    -0.06
    عام
    -0.06
    POSITIVE LOGITS
    eper
    0.07
     депут
    0.07
    .gsub
    0.06
    'une
    0.06
     distilled
    0.06
    žit
    0.06
     format
    0.06
     sint
    0.06
    igrated
    0.06
    .rep
    0.06
    Act Density 0.039%

    No Known Activations