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

    Neuronpedia

    INDEX
    Explanations

    quotations/parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ratio
    -0.06
    .INVALID
    -0.06
    ü
    -0.06
     Michaels
    -0.06
    .sqlite
    -0.06
    bitrary
    -0.06
    _resume
    -0.06
     pok
    -0.06
    -Year
    -0.06
     ар
    -0.06
    POSITIVE LOGITS
    .Operator
    0.06
     söylem
    0.06
    etros
    0.06
    )];
    0.06
    Vote
    0.06
    その
    0.06
    완료
    0.06
     }}>↵
    0.06
     LoggerFactory
    0.06
     safer
    0.06
    Act Density 0.039%

    No Known Activations