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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adows
    -0.06
    STM
    -0.06
    _classifier
    -0.06
    โลก
    -0.06
     جهان
    -0.06
     يع
    -0.06
     يم
    -0.06
    Outer
    -0.06
    飯店
    -0.06
    Fig
    -0.06
    POSITIVE LOGITS
    kategori
    0.07
    _hex
    0.07
    -connect
    0.07
    irectory
    0.07
     li
    0.07
    bin
    0.06
    _log
    0.06
    _Report
    0.06
     αυ
    0.06
     Sharing
    0.06
    Act Density 0.055%

    No Known Activations