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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الك
    -0.07
    trusted
    -0.07
     franch
    -0.07
     교
    -0.07
     nich
    -0.07
     Pied
    -0.06
     franchise
    -0.06
     waypoint
    -0.06
     neob
    -0.06
    eczy
    -0.06
    POSITIVE LOGITS
    music
    0.07
    Attachments
    0.06
     restrictions
    0.06
    egrate
    0.06
     mutations
    0.06
    :)
    0.06
     rex
    0.06
     *)
    0.06
    ká
    0.06
    _BUF
    0.06
    Act Density 0.018%

    No Known Activations