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

    Neuronpedia

    INDEX
    Explanations

    into or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     információ
    0.26
     informações
    0.23
    żenie
    0.23
     fikir
    0.23
    acariy
    0.23
    aç
    0.23
    éssel
    0.23
    يبة
    0.22
    usional
    0.22
     информацию
    0.22
    POSITIVE LOGITS
     appropriate
    0.36
     into
    0.35
    into
    0.32
     different
    0.31
    適切な
    0.30
     designated
    0.30
     separate
    0.29
     desired
    0.29
     their
    0.28
     onto
    0.28
    Act Density 0.089%

    No Known Activations