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

    Neuronpedia

    INDEX
    Explanations

    identifiers containing hyphens and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     あなた
    0.82
     ó
    0.81
     savers
    0.79
     ć
    0.78
     você
    0.78
     （
    0.78
     Éd
    0.77
     programs
    0.76
     여러분
    0.75
     hữu
    0.75
    POSITIVE LOGITS
    PR
    1.12
    FB
    1.08
    CA
    1.08
    J
    1.08
    E
    1.07
    AL
    1.07
    Physics
    1.06
    Intro
    1.05
    B
    1.04
    RE
    1.04
    Act Density 0.036%

    No Known Activations