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

    Neuronpedia

    INDEX
    Explanations

    references to academic authors and their works

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

    Appears after "W" or initials

    np_acts-logits-general · gemini-2.0-flash

    W initial followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.47
    jspb
    -0.44
    TRIBUN
    -0.44
    ㌔
    -0.43
    Tikang
    -0.42
    initas
    -0.41
    ⟬
    -0.41
     getItemId
    -0.41
    detroit
    -0.41
     solito
    -0.40
    POSITIVE LOGITS
     W
    0.55
     Wednesdays
    0.55
     שוליים
    0.53
    W
    0.51
     Warriors
    0.49
    waitKey
    0.46
    Woof
    0.46
    ſelf
    0.46
    Wizard
    0.45
     Wizard
    0.45
    Act Density 1.402%

    No Known Activations