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

    Neuronpedia

    INDEX
    Explanations

    references to various types of handles and door hardware

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

    parts of objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wreck
    -0.50
    conditionally
    -0.49
     Dolan
    -0.48
     cras
    -0.47
     оригіналу
    -0.47
    transQ
    -0.46
    Geplaatst
    -0.45
    dega
    -0.45
     Peker
    -0.44
    suit
    -0.44
    POSITIVE LOGITS
     onOptions
    0.51
     ComVisible
    0.48
    HomeAsUpEnabled
    0.45
     dekoratif
    0.43
    koń
    0.40
     JButton
    0.39
    Browse
    0.38
     Erschein
    0.37
    browse
    0.37
     gång
    0.37
    Act Density 0.004%

    No Known Activations