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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spielen
    -0.07
    .Companion
    -0.07
     Earn
    -0.06
    ΕΙΣ
    -0.06
    op
    -0.06
     Nuevo
    -0.06
    electronics
    -0.06
     Yer
    -0.06
    -front
    -0.06
     γ
    -0.06
    POSITIVE LOGITS
     оч
    0.07
    рист
    0.07
     Settlement
    0.07
     treason
    0.07
    iox
    0.06
    .Inject
    0.06
    PathParam
    0.06
    ptides
    0.06
    Textbox
    0.06
    (set
    0.06
    Act Density 0.001%

    No Known Activations