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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'instant
    -0.08
     distinguish
    -0.08
     minimise
    -0.08
    čenja
    -0.08
     minería
    -0.08
    midt
    -0.08
    ABE
    -0.07
     ഇത്ത
    -0.07
    lyk
    -0.07
    ിത്ര
    -0.07
    POSITIVE LOGITS
     mocked
    0.08
     thyroid
    0.08
     temas
    0.08
     setores
    0.08
     организма
    0.08
    胃
    0.08
     Mayo
    0.08
     disciplines
    0.07
     disciplinas
    0.07
     печени
    0.07
    Act Density 0.005%

    No Known Activations