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

    Neuronpedia

    INDEX
    Explanations

    familiar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    403
    -0.07
     rocking
    -0.07
     superstar
    -0.07
     Ingredient
    -0.07
     dışında
    -0.07
     splice
    -0.07
     Nice
    -0.07
    AES
    -0.07
     Comple
    -0.07
     Rounded
    -0.07
    POSITIVE LOGITS
     familiar
    0.11
     familiarity
    0.10
     loneliness
    0.07
     unfamiliar
    0.07
     acquainted
    0.07
     experi
    0.07
    --↵↵
    0.06
    _helpers
    0.06
     그리
    0.06
    νομα
    0.06
    Act Density 0.014%

    No Known Activations