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

    Neuronpedia

    INDEX
    Explanations

    Limitations and possibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     createUser
    -0.07
    versible
    -0.06
     accusations
    -0.06
     slang
    -0.06
    後に
    -0.06
     Shoot
    -0.06
     التش
    -0.06
     prem
    -0.06
    workers
    -0.06
     secretly
    -0.05
    POSITIVE LOGITS
     ydk
    0.07
     hoped
    0.06
    elden
    0.06
    _subplot
    0.06
    ева
    0.06
     дал
    0.06
    grey
    0.06
    罗
    0.06
    Curve
    0.06
     ض
    0.06
    Act Density 0.044%

    No Known Activations