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

    Neuronpedia

    INDEX
    Explanations

    titles of books and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.49
     (
    0.40
     and
    0.38
    ,
    0.37
     In
    0.35
     in
    0.35
    ↵↵
    0.34
    .
    0.34
     the
    0.34
    Good
    0.34
    POSITIVE LOGITS
     නමුත්
    0.42
     ಉತ್ಪನ್ನ
    0.39
    हतक
    0.37
    <unused569>
    0.36
     එහි
    0.34
    壃
    0.34
     ಕ್ಷೇತ್ರದ
    0.34
    <unused1642>
    0.34
    <unused1105>
    0.34
     स्नातक
    0.33
    Act Density 0.003%

    No Known Activations