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

    Neuronpedia

    INDEX
    Explanations

    references to specific issues or problems

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

    "issue" or "issues"

    np_acts-logits-general · gemini-2.0-flash

    issue / issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gön
    -0.66
     sponges
    -0.60
     aceit
    -0.60
    WaitGroup
    -0.59
    \}\\
    -0.57
     שוליים
    -0.55
    VERTIS
    -0.54
    ajaan
    -0.52
     Mestre
    -0.51
     Elvira
    -0.50
    POSITIVE LOGITS
     issues
    1.04
     Issues
    1.03
    Issues
    0.99
    issues
    0.99
     ISSUES
    0.93
     ISSUE
    0.85
    Issue
    0.85
     issue
    0.84
    ISSUES
    0.84
    ISSUE
    0.84
    Act Density 0.075%

    No Known Activations