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

    Neuronpedia

    INDEX
    Explanations

    autocomplete="off"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    臆
    0.39
    羮
    0.38
    🌃
    0.36
    Trimethyl
    0.36
    <unused91>
    0.35
    ρίς
    0.35
     গুগল
    0.34
    🪵
    0.34
    👃
    0.34
    PropertyParam
    0.34
    POSITIVE LOGITS
    www
    0.48
    read
    0.41
    bes
    0.40
    ch
    0.39
    top
    0.39
    t
    0.38
    s
    0.38
    vide
    0.38
    as
    0.38
    zer
    0.38
    Act Density 0.000%

    No Known Activations