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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ve
    -0.06
     erhalten
    -0.06
    �로
    -0.06
     Mean
    -0.06
     -->
↵
    -0.06
     muddy
    -0.06
     **/↵
    -0.06
     softball
    -0.06
    ,assign
    -0.06
    でき
    -0.06
    POSITIVE LOGITS
    ascimento
    0.06
    hots
    0.06
    IENCE
    0.06
     Explosion
    0.06
    ूब
    0.06
     NavController
    0.06
    STRACT
    0.06
    siyon
    0.06
    ення
    0.06
     nop
    0.06
    Act Density 0.192%

    No Known Activations