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

    Neuronpedia

    INDEX
    Explanations

    specifies the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Says
    1.27
     Verkauf
    1.25
     Profits
    1.24
    หลด
    1.23
     zegt
    1.23
     Résultats
    1.22
     Signup
    1.21
     começo
    1.20
    搵
    1.19
    <unused993>
    1.19
    POSITIVE LOGITS
     that
    1.88
    that
    1.85
    That
    1.47
    the
    1.45
     That
    1.25
     bahwa
    1.24
     the
    1.22
    The
    1.21
    In
    1.17
     as
    1.16
    Act Density 0.173%

    No Known Activations