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

    Neuronpedia

    INDEX
    Explanations

    speak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NETWORK
    -0.07
    idding
    -0.07
     cidade
    -0.07
    addEventListener
    -0.06
    tember
    -0.06
    िख
    -0.06
    expected
    -0.06
    ậy
    -0.06
    _rooms
    -0.06
     overwhelmed
    -0.06
    POSITIVE LOGITS
     Sharia
    0.07
     trillion
    0.07
     articulate
    0.07
     Achilles
    0.07
    /domain
    0.07
    となり
    0.06
    .tipo
    0.06
    (cur
    0.06
     Vital
    0.06
    """.
    0.06
    Act Density 0.024%

    No Known Activations