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

    Neuronpedia

    INDEX
    Explanations

    concepts related to community interactions and personal privacy issues

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

    after certain verbs

    np_acts-logits-general · gemini-2.0-flash

    specific contexts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CompleteListener
    -0.30
     half
    -0.29
     Father
    -0.28
     competitivo
    -0.26
     referrerpolicy
    -0.26
    帖最后由
    -0.25
    ichte
    -0.25
    half
    -0.25
    ündig
    -0.24
    ute
    -0.24
    POSITIVE LOGITS
     queſta
    0.69
     témoig
    0.63
     estekak
    0.63
    InjectAttribute
    0.63
     beſch
    0.62
     tartalomajánló
    0.61
    PerformLayout
    0.60
    yntaxException
    0.60
    <unused28>
    0.59
    ஢
    0.59
    Act Density 0.585%

    No Known Activations