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

    Neuronpedia

    INDEX
    Explanations

    Solve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avirus
    -0.07
     Angus
    -0.07
     P
    -0.06
    Dt
    -0.06
    Approx
    -0.06
    ρον
    -0.06
     Jac
    -0.06
    กต
    -0.06
    priority
    -0.06
     cornerback
    -0.06
    POSITIVE LOGITS
    -Benz
    0.07
     moot
    0.07
    LERİ
    0.06
     afterEach
    0.06
     Used
    0.06
     FRE
    0.06
    ]*
    0.06
     routines
    0.06
    ٢
    0.06
     labeled
    0.06
    Act Density 0.002%

    No Known Activations