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

    Neuronpedia

    INDEX
    Explanations

    specific structures and patterns in textual data

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

    Following "in," "the," or "take" followed by "form"

    np_acts-logits-general · gemini-2.0-flash

    takes the form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esModule
    -0.69
    interopRequire
    -0.65
    RegistryLite
    -0.63
    databind
    -0.59
    DataAnnotations
    -0.59
     Maldonado
    -0.57
    )]);
    -0.55
    CreateModel
    -0.55
     متعلقه
    -0.55
    RUnlock
    -0.52
    POSITIVE LOGITS
     form
    2.32
     Form
    1.81
     forms
    1.81
    form
    1.74
    Form
    1.65
     bentuk
    1.64
     FORM
    1.63
     Forms
    1.63
     vorm
    1.54
     forma
    1.52
    Act Density 0.499%

    No Known Activations