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

    Neuronpedia

    INDEX
    Explanations

    ket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disrupt
    -0.07
    ذي
    -0.07
    ディ
    -0.06
    +"/
    -0.06
    -0.06
    接着
    -0.06
     fue
    -0.06
    рез
    -0.06
    를
    -0.06
    label
    -0.06
    POSITIVE LOGITS
    ความร
    0.08
    renom
    0.07
    結
    0.07
    -selector
    0.06
    ümüz
    0.06
     kes
    0.06
    ableOpacity
    0.06
    .`|`↵
    0.06
    _UDP
    0.06
    alternative
    0.06
    Act Density 0.012%

    No Known Activations