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

    Neuronpedia

    INDEX
    Explanations

    а

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     famous
    -0.07
    incy
    -0.07
    رير
    -0.07
     można
    -0.06
     Raw
    -0.06
    μιο
    -0.06
    lanan
    -0.06
    _wave
    -0.06
     мень
    -0.06
    spe
    -0.06
    POSITIVE LOGITS
     REST
    0.06
     accessing
    0.06
    eligible
    0.06
    (true
    0.06
    vest
    0.06
     Erie
    0.06
     ků
    0.06
     getS
    0.06
     access
    0.06
     flex
    0.06
    Act Density 0.000%

    No Known Activations