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

    Neuronpedia

    INDEX
    Explanations

    structures and patterns in data formatting

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

    array indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.56
    цездатний
    -0.56
    TagMode
    -0.54
    Geplaatst
    -0.52
     snippetHide
    -0.52
    onOptions
    -0.51
    }}]{
    -0.51
    تقاوى
    -0.49
    AutoModerator
    -0.49
    Bibliograf
    -0.49
    POSITIVE LOGITS
     kaksi
    0.44
     conjunta
    0.44
     bailarina
    0.44
     quieran
    0.43
     correctes
    0.41
     redonda
    0.41
     fédéral
    0.41
     notare
    0.41
     indipendente
    0.41
     głos
    0.40
    Act Density 0.021%

    No Known Activations