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

    Neuronpedia

    INDEX
    Explanations

    CSS styling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     animations
    -0.06
    “And
    -0.06
    _ING
    -0.06
    -origin
    -0.06
    δα
    -0.06
     animation
    -0.06
     Parties
    -0.06
    ematics
    -0.06
    (network
    -0.06
    ogo
    -0.06
    POSITIVE LOGITS
    .Feature
    0.07
    emodel
    0.07
    luet
    0.06
     л
    0.06
    .netflix
    0.06
    %)↵↵
    0.06
     fired
    0.06
    ;?>
    0.06
     closets
    0.06
     warped
    0.06
    Act Density 0.011%

    No Known Activations