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

    Neuronpedia

    INDEX
    Explanations

    support costs, help, questions, request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x9B>
    0.35
    \
    0.34
    <0xAB>
    0.31
    {
    0.31
    ?
    0.27
    <0x95>
    0.27
    ซึ่ง
    0.26
     examining
    0.26
     kepentingan
    0.26
    <0x9A>
    0.25
    POSITIVE LOGITS
    ad
    0.51
    es
    0.49
    i
    0.48
    g
    0.44
    x
    0.44
    ab
    0.43
    d
    0.43
    P
    0.43
    et
    0.42
    on
    0.42
    Act Density 0.633%

    No Known Activations