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

    Neuronpedia

    INDEX
    Explanations

    movie reviews and writings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roma
    -0.07
    -girl
    -0.07
     Controller
    -0.07
     predicts
    -0.06
     Outlook
    -0.06
     во
    -0.06
     rè
    -0.06
    ентами
    -0.06
    .GL
    -0.06
    levision
    -0.06
    POSITIVE LOGITS
    ―
    0.07
    _QU
    0.06
     ∀
    0.06
    .movies
    0.06
    ”，
    0.06
     yyn
    0.06
    .listBox
    0.06
     zs
    0.06
    Chapter
    0.06
    _CUSTOM
    0.06
    Act Density 0.136%

    No Known Activations