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

    Neuronpedia

    INDEX
    Explanations

    opening quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     é
    1.32
     al
    1.29
     b
    1.29
     juga
    1.29
     zu
    1.28
     etiquette
    1.25
     database
    1.22
     et
    1.21
     sale
    1.20
    💟
    1.20
    POSITIVE LOGITS
    For
    1.99
    This
    1.94
    The
    1.93
    If
    1.92
    It
    1.90
    We
    1.90
    When
    1.88
    As
    1.85
    In
    1.85
    There
    1.84
    Act Density 0.226%

    No Known Activations