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

    Neuronpedia

    INDEX
    Explanations

    technical terms and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    1.69
    o
    1.61
    y
    1.40
    el
    1.35
    os
    1.32
    d
    1.31
    oak
    1.30
    k
    1.25
    as
    1.18
    f
    1.18
    POSITIVE LOGITS
     faults
    1.23
     rollerskates
    1.20
     buns
    1.13
     magnétique
    1.13
     visites
    1.10
     tailles
    1.08
     parfaite
    1.07
     последнего
    1.04
     curtains
    1.02
     monomials
    1.02
    Act Density 1.267%

    No Known Activations