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

    Neuronpedia

    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gap
    -0.07
    vil
    -0.06
    '|
    -0.06
     yapmak
    -0.06
     tox
    -0.06
     rant
    -0.06
    اوية
    -0.06
    +x
    -0.06
     حي
    -0.06
    치
    -0.06
    POSITIVE LOGITS
    HER
    0.09
    ER
    0.08
    BER
    0.08
    ."</
    0.07
    ]initWith
    0.07
    EL
    0.07
     endeavors
    0.07
    ')</
    0.07
    ERS
    0.07
    _COMPLETED
    0.07
    Act Density 0.076%

    No Known Activations