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

    Neuronpedia

    INDEX
    Explanations

    URLs and references related to online resources and coding repositories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acherous
    -0.44
    ecuted
    -0.42
    transQ
    -0.41
     Administrativna
    -0.41
     createSlice
    -0.40
    flashdata
    -0.40
    েই
    -0.40
     trekken
    -0.39
     Schreiber
    -0.39
     Features
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.65
     transfieras
    0.58
    AccessorTable
    0.50
     Normdatei
    0.49
    ($__
    0.45
    saraba
    0.44
    AddTagHelper
    0.44
     autorytatywna
    0.43
    nologue
    0.42
    +#+
    0.42
    Act Density 0.001%

    No Known Activations