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

    Neuronpedia

    INDEX
    Explanations

    Optimization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laurent
    -0.08
    connexion
    -0.08
     દર્શ
    -0.08
     схем
    -0.07
     dominance
    -0.07
     Cindy
    -0.07
    -space
    -0.07
     ub
    -0.07
     lantern
    -0.07
    Leb
    -0.07
    POSITIVE LOGITS
    spent
    0.08
    JECT
    0.08
     pollo
    0.08
     Constraints
    0.08
    afile
    0.08
    IMPORTANT
    0.07
     hemorrho
    0.07
     brutally
    0.07
    elfare
    0.07
    head
    0.07
    Act Density 0.001%

    No Known Activations