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

    Neuronpedia

    INDEX
    Explanations

    Random text and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proofs
    -0.60
    __(/*!
    -0.56
     prints
    -0.54
     mistakes
    -0.54
     decisions
    -0.54
     cuttings
    -0.53
     charité
    -0.53
     errors
    -0.53
     papers
    -0.52
     numbers
    -0.52
    POSITIVE LOGITS
    HasIndex
    0.61
     المعيارى
    0.56
     surla
    0.54
     eventdata
    0.52
     виправивши
    0.51
     通販
    0.51
    eschön
    0.51
     kasarigan
    0.51
     load
    0.50
     متعلقه
    0.49
    Act Density 0.000%

    No Known Activations