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

    Neuronpedia

    INDEX
    Explanations

    JSON data structures

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

    Code, numbers, or special characters

    np_acts-logits-general · gemini-2.0-flash

    numbered task or item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bech
    -0.54
     تضيفلها
    -0.53
    }),
    -0.49
    ارية
    -0.47
    DebuggerStep
    -0.45
    AppComponent
    -0.44
    mbles
    -0.44
    ItemGroup
    -0.44
    CASS
    -0.44
    ftar
    -0.43
    POSITIVE LOGITS
     StringVar
    0.63
    expandindo
    0.59
     autorytatywna
    0.58
     autopilot
    0.58
     マイク
    0.54
    ագրություններ
    0.53
    rittura
    0.53
     समीक्षक
    0.52
    âce
    0.52
    ελ
    0.50
    Act Density 0.035%

    No Known Activations