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

    Neuronpedia

    INDEX
    Explanations

    ={

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pop
    -0.07
     muy
    -0.07
     гри
    -0.07
     fø
    -0.07
     '.';↵
    -0.07
     comer
    -0.07
    _isr
    -0.07
    ваем
    -0.07
    !!}↵
    -0.07
     lesbians
    -0.07
    POSITIVE LOGITS
    ={
    0.07
     propositions
    0.07
     volume
    0.06
    movies
    0.06
     Staff
    0.06
    onent
    0.06
    ioni
    0.06
    isation
    0.06
    YYYY
    0.06
    uent
    0.06
    Act Density 0.002%

    No Known Activations