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

    Neuronpedia

    INDEX
    Explanations

    references to "mini" or "minimized" concepts or items

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

    mini and miniature items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    athies
    -0.49
     betweenstory
    -0.46
    atorship
    -0.45
    argout
    -0.44
    forKey
    -0.42
    :`
    -0.41
    ERSHIP
    -0.41
     Umgang
    -0.41
    راسیون
    -0.39
    bcryptjs
    -0.39
    POSITIVE LOGITS
     mini
    2.27
    Mini
    2.02
    mini
    1.97
     Mini
    1.94
     MINI
    1.60
     miniature
    1.57
    MINI
    1.55
     мини
    1.34
    miniature
    1.34
    ミニ
    1.33
    Act Density 0.003%

    No Known Activations