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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to experimental data or measurements

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

    numerical data and references to quantities

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

    reflexive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mockito
    -0.47
    kuuta
    -0.45
    brainly
    -0.44
     today
    -0.43
    nextDouble
    -0.43
    tagHelper
    -0.42
     se
    -0.41
     tarto
    -0.41
    固
    -0.41
    ILD
    -0.40
    POSITIVE LOGITS
     myſelf
    0.80
     themſelves
    0.78
     itſelf
    0.77
     himſelf
    0.76
    ſelves
    0.74
     poffible
    0.73
     reaſon
    0.73
     muſt
    0.72
     becauſe
    0.71
    AndEndTag
    0.71
    Act Density 0.125%

    No Known Activations