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

    Neuronpedia

    INDEX
    Explanations

    URLs after keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convective
    0.37
    SANIT
    0.37
    قطه
    0.36
    াহরণ
    0.35
     connotations
    0.35
     mucous
    0.35
    اونلو
    0.34
    䊂
    0.34
     సన్నివేశ
    0.34
    arrêté
    0.34
    POSITIVE LOGITS
    /
    0.94
    /?
    0.65
    /[
    0.63
    /%
    0.61
    /)
    0.60
    /(
    0.59
    /{
    0.59
    /.
    0.57
    /${
    0.55
    /,
    0.55
    Act Density 0.039%

    No Known Activations