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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胜
    -0.07
     Pokémon
    -0.07
     backing
    -0.07
     Archie
    -0.07
    らの
    -0.06
     což
    -0.06
     stockings
    -0.06
     liberty
    -0.06
     Hire
    -0.06
     Status
    -0.06
    POSITIVE LOGITS
    ague
    0.06
     adult
    0.06
    swana
    0.06
    !↵↵
    0.06
    EDGE
    0.06
    μοί
    0.06
    inee
    0.06
    odox
    0.06
    ança
    0.06
    ürger
    0.06
    Act Density 0.017%

    No Known Activations