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

    Neuronpedia

    INDEX
    Explanations

    work on tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಕಂಚ
    0.55
    ździe
    0.48
    ст
    0.47
    smittel
    0.47
     к
    0.46
     плюс
    0.46
    getImageFolder
    0.46
     тысяч
    0.45
     ደቂ
    0.45
    NESS
    0.45
    POSITIVE LOGITS
    ong
    0.67
     he
    0.58
     We
    0.56
     you
    0.55
     it
    0.55
    การ
    0.55
     be
    0.54
     You
    0.53
    et
    0.52
    </strong>
    0.50
    Act Density 0.002%

    No Known Activations