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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serait
    -0.07
    媒
    -0.07
    dia
    -0.07
    }}>
    -0.07
     解
    -0.06
    圢
    -0.06
    지
    -0.06
    昂
    -0.06
    TARGET
    -0.06
    食べた
    -0.06
    POSITIVE LOGITS
    azen
    0.07
     specs
    0.07
    _PRED
    0.07
    .records
    0.07
     shopping
    0.07
    当年
    0.07
    udeau
    0.07
     surfing
    0.07
     lbs
    0.07
    伾
    0.07
    Act Density 0.013%

    No Known Activations