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

    Neuronpedia

    INDEX
    Explanations

    say delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regenerated
    -0.07
    ไร
    -0.07
    ...');↵
    -0.07
     Overs
    -0.07
    41
    -0.07
     izin
    -0.07
    /j
    -0.06
    -D
    -0.06
     sperm
    -0.06
    ný
    -0.06
    POSITIVE LOGITS
     destino
    0.07
     seperate
    0.06
    .OutputStream
    0.06
     cloves
    0.06
    	pc
    0.06
     metic
    0.06
     ου
    0.06
     attic
    0.06
     本
    0.06
    osite
    0.06
    Act Density 0.028%

    No Known Activations