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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scams
    -0.07
    ’int
    -0.07
    af
    -0.07
    :")
    -0.07
    System
    -0.07
    'int
    -0.06
    ／
    -0.06
     desta
    -0.06
    orean
    -0.06
     wants
    -0.06
    POSITIVE LOGITS
    (GL
    0.07
    .echo
    0.06
    formData
    0.06
    lical
    0.06
    ught
    0.06
     dispute
    0.06
    _cut
    0.06
     migrating
    0.06
     setId
    0.06
    OfWork
    0.06
    Act Density 0.000%

    No Known Activations