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

    Neuronpedia

    INDEX
    Explanations

    names of characters and entities

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

    Japanese names ending in iro or Taro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.58
     resourceCulture
    -0.55
     ویکی‌پدی
    -0.50
     Chwiliwch
    -0.47
     covenants
    -0.44
     aapt
    -0.44
    @(
    -0.43
    }');
    -0.42
    ]")]
    -0.42
    cete
    -0.42
    POSITIVE LOGITS
    jiro
    0.50
    osuke
    0.48
    ichiro
    0.46
    suke
    0.45
    太郎
    0.44
    皙
    0.41
     houſe
    0.41
    writeFieldEnd
    0.40
    WriteBarrier
    0.39
     Púb
    0.39
    Act Density 0.048%

    No Known Activations