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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    浓郁
    -0.07
    _f
    -0.07
     m
    -0.07
    맻
    -0.07
    (m
    -0.07
    ḯ
    -0.07
    ,m
    -0.07
    ꦇ
    -0.07
    单一
    -0.07
    并不多
    -0.07
    POSITIVE LOGITS
     urlparse
    0.07
     PLAYER
    0.07
     Dept
    0.07
    że
    0.07
    ;.
    0.07
     Branch
    0.07
     の
    0.06
    lest
    0.06
     stored
    0.06
     Soon
    0.06
    Act Density 0.002%

    No Known Activations