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

    Neuronpedia

    INDEX
    Explanations

    terms related to exceptional performance or uniqueness

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

    outstanding exceptional notables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nawr
    -0.57
    AxisAlignment
    -0.51
     utafitiHapana
    -0.51
    ktm
    -0.50
     LoginForm
    -0.50
     BoxDecoration
    -0.49
    FormTagHelper
    -0.49
    VIAF
    -0.49
    DockStyle
    -0.49
    laceae
    -0.48
    POSITIVE LOGITS
     standout
    1.82
    Notable
    0.80
     outstanding
    0.76
     Notable
    0.76
     notable
    0.75
     destacados
    0.73
     noteworthy
    0.73
     highlight
    0.72
     destacado
    0.72
    Outstanding
    0.72
    Act Density 0.002%

    No Known Activations