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

    Neuronpedia

    INDEX
    Explanations

    defined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expect
    -0.06
    ανα
    -0.06
     campaigning
    -0.06
    monster
    -0.06
    .gz
    -0.06
    かし
    -0.06
     보면
    -0.06
     تكون
    -0.06
     широк
    -0.06
     flowing
    -0.06
    POSITIVE LOGITS
    (dictionary
    0.06
     +:+
    0.06
    _Cell
    0.06
     distracted
    0.06
     reproductive
    0.06
     aggression
    0.06
    Pink
    0.06
     Quint
    0.06
    ':"
    0.06
    -os
    0.06
    Act Density 0.006%

    No Known Activations