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

    Neuronpedia

    INDEX
    Explanations

    acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getEmail
    -0.08
    ,DB
    -0.07
     number
    -0.06
     Rect
    -0.06
     Collider
    -0.06
     Discussions
    -0.06
     cells
    -0.06
    uba
    -0.06
    .Enc
    -0.06
    Uses
    -0.06
    POSITIVE LOGITS
     ankles
    0.06
    ція
    0.06
     práci
    0.06
    tri
    0.06
    동
    0.06
    队
    0.06
     ration
    0.06
     inspire
    0.06
     vých
    0.06
    248
    0.06
    Act Density 0.071%

    No Known Activations