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

    Neuronpedia

    INDEX
    Explanations

    locations mentioned in the text

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

    here in [location]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.39
    antd
    -0.39
     ſtre
    -0.38
     uſed
    -0.38
     serai
    -0.37
     Pohl
    -0.36
     devriez
    -0.35
     diable
    -0.35
    osoba
    -0.35
     Prata
    -0.34
    POSITIVE LOGITS
    脚注の使い方
    0.71
    NameInMap
    0.68
     endregion
    0.63
    OGND
    0.63
     مشين
    0.61
    󠁢
    0.59
    here
    0.59
     kaarangay
    0.58
    CodeAttribute
    0.58
    ⟬
    0.57
    Act Density 0.006%

    No Known Activations