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

    Neuronpedia

    INDEX
    Explanations

    Code Snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Layer
    -0.07
    lix
    -0.06
     Prison
    -0.06
     Alien
    -0.06
     Fant
    -0.06
     Naughty
    -0.06
     Joseph
    -0.06
    Nice
    -0.06
     Strings
    -0.06
    *r
    -0.06
    POSITIVE LOGITS
    CTIONS
    0.07
     Conn
    0.07
     paw
    0.07
     chez
    0.06
    ARG
    0.06
     pac
    0.06
    PCI
    0.06
    iron
    0.06
    (min
    0.06
    .mutex
    0.06
    Act Density 0.003%

    No Known Activations