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

    Neuronpedia

    INDEX
    Explanations

    clauses after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hepinize
    1.11
     (!)
    1.10
     (!
    1.09
    !:
    1.06
     ¡
    1.03
    (!)
    1.00
     !,
    0.93
    !..
    0.93
    ¡
    0.89
    !,
    0.89
    POSITIVE LOGITS
     though
    0.96
    Though
    0.92
    though
    0.88
    which
    0.88
     which
    0.83
     there
    0.81
     yg
    0.78
     they
    0.77
    说是
    0.76
     purview
    0.75
    Act Density 0.010%

    No Known Activations