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

    Neuronpedia

    INDEX
    Explanations

    environmental impact assessments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     伊
    -0.07
     Ish
    -0.07
    Week
    -0.07
     P
    -0.07
     Ste
    -0.07
    Ad
    -0.07
    Alert
    -0.07
     Museum
    -0.06
     VH
    -0.06
     Weber
    -0.06
    POSITIVE LOGITS
    .CurrentRow
    0.07
    状況
    0.06
    .central
    0.06
     आदम
    0.06
     REPL
    0.06
    _budget
    0.06
     ebx
    0.06
    }}],↵
    0.06
     жінок
    0.06
    ，还
    0.06
    Act Density 0.021%

    No Known Activations