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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hospitals
    -0.07
    _gift
    -0.07
     Those
    -0.07
    Prosec
    -0.07
    oping
    -0.07
    계획
    -0.07
    facility
    -0.07
    \",↵
    -0.06
    -average
    -0.06
    阶
    -0.06
    POSITIVE LOGITS
     Tune
    0.06
     tekrar
    0.06
    jas
    0.06
    /post
    0.06
     radicals
    0.06
    /Login
    0.06
    .toLowerCase
    0.06
     अल
    0.06
    .vertical
    0.06
     });↵↵
    0.05
    Act Density 0.015%

    No Known Activations