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

    Neuronpedia

    INDEX
    Explanations

    questions/pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    input
    -0.06
     sea
    -0.06
    热
    -0.06
    76
    -0.06
     Thief
    -0.06
    ��
    -0.06
     Muslims
    -0.06
    battle
    -0.06
     smoke
    -0.06
     Пет
    -0.06
    POSITIVE LOGITS
    umbotron
    0.07
    AccessException
    0.07
    CHED
    0.07
    ORIGINAL
    0.07
    .setIcon
    0.07
    辰
    0.07
    alore
    0.07
    _THIS
    0.06
    xxxx
    0.06
    &ZeroWidthSpace
    0.06
    Act Density 0.035%

    No Known Activations