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

    Neuronpedia

    INDEX
    Explanations

    deep dive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kereta
    0.43
     గొప్ప
    0.40
     unfolded
    0.39
     terr
    0.39
     klient
    0.39
     offrent
    0.38
    namento
    0.38
     offre
    0.38
    жко
    0.37
     tiennent
    0.37
    POSITIVE LOGITS
    <h1>
    0.40
    тал
    0.39
     Jian
    0.37
     Economies
    0.37
    conect
    0.36
    ulsive
    0.36
    doi
    0.35
    Else
    0.35
    љи
    0.35
    そこに
    0.35
    Act Density 0.007%

    No Known Activations