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

    Neuronpedia

    INDEX
    Explanations

    references to "things" or unspecified objects in various contexts

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

    generic thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.45
     jsPsych
    -0.44
     boste
    -0.43
    lukan
    -0.41
     karet
    -0.41
     resourceCulture
    -0.40
    isContained
    -0.40
    gdx
    -0.40
     encu
    -0.39
    ArrowToggle
    -0.39
    POSITIVE LOGITS
     THING
    0.69
     thing
    0.68
    Thing
    0.65
     Thing
    0.65
     stuff
    0.57
     thingy
    0.56
    Stuff
    0.54
     cosas
    0.54
     Stuff
    0.53
     coisas
    0.53
    Act Density 0.160%

    No Known Activations