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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    มหานคร
    -0.07
    groupBy
    -0.07
    (stderr
    -0.06
     الدم
    -0.06
     القدم
    -0.06
     сок
    -0.06
    �江
    -0.06
     extent
    -0.06
     quando
    -0.06
    وية
    -0.06
    POSITIVE LOGITS
    =false
    0.08
    _CHANNEL
    0.07
     ple
    0.06
     poignant
    0.06
    uyến
    0.06
     Grey
    0.06
    kee
    0.06
    ơ
    0.06
    714
    0.06
     dumb
    0.06
    Act Density 0.038%

    No Known Activations