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

    Neuronpedia

    INDEX
    Explanations

    references to software bugs and issues related to programming

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

    Software bugs and issues

    np_acts-logits-general · gemini-2.0-flash

    bugs and flaws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.41
     houſe
    -0.40
     utafitiHapana
    -0.37
     Chwiliwch
    -0.36
     renewal
    -0.35
    ViewFeatures
    -0.33
    ſelf
    -0.33
     viſ
    -0.33
     Houſe
    -0.33
    ArrowToggle
    -0.33
    POSITIVE LOGITS
     flaw
    0.57
     glitches
    0.55
     glitch
    0.54
     bugged
    0.47
     flawed
    0.47
    AISSEE
    0.47
     bug
    0.47
     erroneous
    0.46
     cruelly
    0.46
    rungsseite
    0.45
    Act Density 0.517%

    No Known Activations