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

    Neuronpedia

    INDEX
    Explanations

    /detail

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♾
    -0.07
     Jets
    -0.07
    Magic
    -0.07
    ⌦
    -0.07
    蕺
    -0.07
    Collections
    -0.06
    operations
    -0.06
    _texts
    -0.06
    icles
    -0.06
    utes
    -0.06
    POSITIVE LOGITS
    _playing
    0.07
    疗效
    0.07
    0.07
    公章
    0.07
     numerical
    0.07
     Single
    0.07
     suspense
    0.07
     therapeutic
    0.07
     LD
    0.06
    在我
    0.06
    Act Density 0.000%

    No Known Activations