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

    Neuronpedia

    INDEX
    Explanations

    movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xuất
    -0.07
     dispos
    -0.07
    Cu
    -0.06
     Jin
    -0.06
    .ly
    -0.06
     رمز
    -0.06
     concise
    -0.06
    항
    -0.06
    uC
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Films
    0.07
    CORD
    0.06
     happening
    0.06
    ابة
    0.06
    andon
    0.06
    _branch
    0.06
     Danish
    0.06
     German
    0.06
     pretrained
    0.06
    ัตว
    0.06
    Act Density 0.035%

    No Known Activations