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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives related to size or magnitude

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

    comparative magnitudes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carriera
    -0.41
     comm
    -0.38
    scienced
    -0.38
    compar
    -0.37
    AnchorTagHelper
    -0.37
     instead
    -0.37
     various
    -0.36
    뀔
    -0.36
    !*\
    -0.36
    /******/
    -0.35
    POSITIVE LOGITS
     للاسماء
    0.60
    Personendaten
    0.58
    principalColumn
    0.57
     Económica
    0.53
    TestingModule
    0.52
     Técnicas
    0.50
     aveug
    0.49
     často
    0.49
     esetben
    0.48
    脚注の使い方
    0.48
    Act Density 0.081%

    No Known Activations