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

    Neuronpedia

    INDEX
    Explanations

    transmitting genes, values, and knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    1.27
    <0x80>
    1.18
    ０
    1.17
    0
    0.95
    ၀
    0.89
    기
    0.86
    ००
    0.84
     laterales
    0.83
    場合の
    0.82
    ج
    0.80
    POSITIVE LOGITS
    ו
    0.89
     it
    0.87
    st
    0.82
    S
    0.82
    the
    0.82
    un
    0.82
    K
    0.81
     be
    0.78
     transmit
    0.78
    y
    0.78
    Act Density 0.002%

    No Known Activations