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

    Neuronpedia

    INDEX
    Explanations

    circle-related code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -serving
    -0.08
    airport
    -0.07
     valido
    -0.07
    ultimo
    -0.07
     troubling
    -0.06
     Burger
    -0.06
     orgy
    -0.06
     Hundred
    -0.06
     Gow
    -0.06
    Emp
    -0.06
    POSITIVE LOGITS
    Emb
    0.07
    -modal
    0.07
    .Collapsed
    0.06
     Reputation
    0.06
     необ
    0.06
     Active
    0.06
     Rhe
    0.06
    ind
    0.06
    USB
    0.06
     Rel
    0.05
    Act Density 0.011%

    No Known Activations