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

    Neuronpedia

    INDEX
    Explanations

    code structure and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mute
    0.49
     attén
    0.46
     lésions
    0.45
     réf
    0.45
     for
    0.45
     moy
    0.44
     mesure
    0.43
     méth
    0.42
     cận
    0.42
     степени
    0.41
    POSITIVE LOGITS
    aj
    0.52
    jal
    0.47
    0.45
    endif
    0.45
    end
    0.45
    acas
    0.44
    ified
    0.44
    ve
    0.44
    merged
    0.44
    Very
    0.44
    Act Density 0.000%

    No Known Activations