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

    Neuronpedia

    INDEX
    Explanations

    expressions of size or magnitude

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

    magnitude and scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vege
    -0.62
     alibi
    -0.61
    astify
    -0.61
    ashqai
    -0.60
    bibfield
    -0.56
    Nucle
    -0.56
     Rhy
    -0.55
     rhy
    -0.55
    richTextPanel
    -0.55
    Rhy
    -0.55
    POSITIVE LOGITS
     immense
    1.48
     tremendous
    1.11
    mense
    1.06
     enormous
    1.05
     immensely
    0.99
     huge
    0.95
    menso
    0.94
     vast
    0.93
     massive
    0.87
     ogrom
    0.87
    Act Density 0.003%

    No Known Activations