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

    Neuronpedia

    INDEX
    Explanations

    form/feeling/real

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TH
    0.78
    xj
    0.75
    ці
    0.73
    cert
    0.73
    nginx
    0.71
    UR
    0.70
     PGE
    0.70
    ULF
    0.70
    เซีย
    0.69
    OL
    0.69
    POSITIVE LOGITS
     কখনও
    0.73
     suffisamment
    0.73
    能夠
    0.72
     وفا
    0.71
     "
    0.71
     outras
    0.70
     cadeau
    0.69
     annen
    0.69
     badly
    0.69
    ında
    0.68
    Act Density 0.000%

    No Known Activations