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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chains
    -0.07
     Liz
    -0.07
     lunch
    -0.06
    hash
    -0.06
    éis
    -0.06
    oned
    -0.06
     Mark
    -0.06
    LOUR
    -0.06
    λώ
    -0.06
    ará
    -0.06
    POSITIVE LOGITS
     Infant
    0.07
     findById
    0.07
    <Class
    0.06
     Dynam
    0.06
    pow
    0.06
     ############################################################################
    0.06
    	Simple
    0.06
     foundation
    0.06
     innocent
    0.06
    .modified
    0.06
    Act Density 0.005%

    No Known Activations