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

    Neuronpedia

    INDEX
    Explanations

    agreement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DEFIN
    -0.06
    .digest
    -0.06
    matches
    -0.06
     ovšem
    -0.06
     Into
    -0.06
    iedades
    -0.06
     dispute
    -0.06
    分析
    -0.06
    .epoch
    -0.06
     Desktop
    -0.06
    POSITIVE LOGITS
     Colleg
    0.07
     začala
    0.07
     focal
    0.06
    ==(
    0.06
    nex
    0.06
    042
    0.06
     Mult
    0.06
     violates
    0.06
     useMemo
    0.06
    	d
    0.06
    Act Density 0.004%

    No Known Activations