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

    Neuronpedia

    INDEX
    Explanations

    positive action verbs and terms that convey growth or assistance

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

    introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.71
    ंदीखरीदारी
    -0.69
    PerformLayout
    -0.52
    RenderAtEndOf
    -0.48
     desmotivaciones
    -0.48
    mercato
    -0.48
    ⟬
    -0.47
     soltanto
    -0.46
    styleType
    -0.46
     memanfaatkan
    -0.45
    POSITIVE LOGITS
    Notae
    0.44
     pep
    0.43
    LO
    0.40
    wpi
    0.38
    Virginia
    0.36
    BO
    0.35
    DataBinding
    0.35
    Pranala
    0.35
     Olms
    0.35
    oltán
    0.35
    Act Density 0.033%

    No Known Activations