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

    Neuronpedia

    INDEX
    Explanations

    product facing broader audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    புக
    0.47
    भागी
    0.46
    नहीं
    0.46
     warmly
    0.45
     descubre
    0.45
     heartily
    0.43
    त्सा
    0.43
    generic
    0.42
     parte
    0.42
     டை
    0.42
    POSITIVE LOGITS
    UpperCase
    0.48
    {:
    0.46
    اخ
    0.45
    ormous
    0.45
     waven
    0.45
    给出
    0.44
    رف
    0.44
    \
    0.44
    lf
    0.43
    Pclass
    0.43
    Act Density 0.000%

    No Known Activations