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

    Neuronpedia

    INDEX
    Explanations

    author initials in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     грошы
    0.32
    禳
    0.31
     паліты
    0.30
     полицей
    0.29
    谲
    0.29
    观念
    0.28
    酺
    0.28
     стаўкі
    0.28
     деньги
    0.28
     നിയമ
    0.28
    POSITIVE LOGITS
     et
    0.41
    {\'
    0.38
     researchers
    0.35
     and
    0.34
    us
    0.34
    un
    0.34
    io
    0.33
    {\
    0.33
     collaborators
    0.33
    en
    0.33
    Act Density 0.012%

    No Known Activations