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

    Neuronpedia

    INDEX
    Explanations

    array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worms
    -0.07
    non
    -0.07
    dup
    -0.06
    ="--
    -0.06
    .writ
    -0.06
     Anything
    -0.06
    ohan
    -0.06
     部
    -0.06
    Digite
    -0.06
    event
    -0.06
    POSITIVE LOGITS
     taraf
    0.07
     trav
    0.07
     psi
    0.07
    _CLICKED
    0.07
     vzdělávání
    0.07
    antium
    0.06
    itive
    0.06
     Beitrag
    0.06
    ψη
    0.06
    nesota
    0.06
    Act Density 0.084%

    No Known Activations