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

    Neuronpedia

    INDEX
    Explanations

    error messages and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    3.17
    :**
    2.13
    -:
    2.08
    :*
    2.06
    :-
    2.06
    :>
    1.96
    :...
    1.95
    :“
    1.90
    :$
    1.89
    :]
    1.88
    POSITIVE LOGITS
    ‬‬
    1.72
     ܠ
    1.43
     phosphatase
    1.37
     phonon
    1.37
     parr
    1.36
     phonons
    1.34
     ¡
    1.31
     meny
    1.29
     effectivement
    1.29
     PropTypes
    1.28
    Act Density 0.748%

    No Known Activations