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

    Neuronpedia

    INDEX
    Explanations

    explaining what and how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    they
    0.30
    also
    0.27
    ↵
    0.25
     Aspects
    0.24
     lui
    0.24
    the
    0.24
    のか
    0.24
     aspek
    0.23
    They
    0.23
    from
    0.23
    POSITIVE LOGITS
     sorts
    0.35
     both
    0.30
     what
    0.29
     our
    0.28
     how
    0.28
     these
    0.27
     this
    0.26
     their
    0.26
     those
    0.26
     its
    0.26
    Act Density 0.682%

    No Known Activations