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

    Neuronpedia

    INDEX
    Explanations

    yaml code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defens
    0.46
     determinante
    0.43
     granulation
    0.41
     coag
    0.41
    жина
    0.39
     utili
    0.39
     imper
    0.39
     stabilit
    0.38
    鄒
    0.38
     DIEGO
    0.38
    POSITIVE LOGITS
    ---
    0.71
    #
    0.69
    name
    0.59
     ---
    0.59
    section
    0.55
    title
    0.54
    yaml
    0.54
    --
    0.52
    apiVersion
    0.52
    ###
    0.51
    Act Density 0.027%

    No Known Activations