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

    Neuronpedia

    INDEX
    Explanations

    for loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “I
    -0.07
    पन
    -0.07
    epar
    -0.07
    мещ
    -0.07
     جدا
    -0.07
     condom
    -0.06
    料理
    -0.06
    írk
    -0.06
     الآ
    -0.06
     part
    -0.06
    POSITIVE LOGITS
    vrolet
    0.07
    鳥
    0.07
     traged
    0.06
    üns
    0.06
     �
    0.06
    (diff
    0.06
     theoret
    0.06
     Ra
    0.06
    _eps
    0.06
    َح
    0.06
    Act Density 0.030%

    No Known Activations