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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .about
    -0.08
     Jude
    -0.07
    middleware
    -0.06
     Rudy
    -0.06
    Martin
    -0.06
     lucr
    -0.06
     digestive
    -0.06
     nive
    -0.06
     dispos
    -0.06
    OH
    -0.06
    POSITIVE LOGITS
    entanyl
    0.06
    -elements
    0.06
    Grad
    0.06
    imension
    0.06
    StringEncoding
    0.06
    _ANY
    0.06
    AndPassword
    0.06
    ebp
    0.06
    DonaldTrump
    0.06
     shady
    0.06
    Act Density 0.016%

    No Known Activations