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

    Neuronpedia

    INDEX
    Explanations

    Performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infl
    -0.07
     colonial
    -0.06
     tox
    -0.06
    unding
    -0.06
     shortcomings
    -0.06
     AUX
    -0.06
    venile
    -0.06
     иметь
    -0.06
     ql
    -0.06
     *
↵
    -0.06
    POSITIVE LOGITS
    ...');↵
    0.07
     відк
    0.07
    _numero
    0.07
    neck
    0.07
    .mem
    0.07
    Driving
    0.06
     sqlSession
    0.06
     cậu
    0.06
    urgy
    0.06
    ไทย
    0.06
    Act Density 0.275%

    No Known Activations