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

    Neuronpedia

    INDEX
    Explanations

    names of family members and their relationships

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

    Mathematical or technical expressions

    np_acts-logits-general · gemini-2.0-flash

    word followed by specific word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.80
    NameInMap
    -0.71
     مشين
    -0.68
    下载附件
    -0.65
     pinulongan
    -0.64
    -0.59
    __':
    -0.59
    SourceChecksum
    -0.58
    PreInfinity
    -0.56
    kháu
    -0.55
    POSITIVE LOGITS
     care
    0.56
     onAnimation
    0.56
    ((
    0.54
     kép
    0.52
     steward
    0.51
     cared
    0.51
     Care
    0.51
     kag
    0.50
    lüssel
    0.50
    گاری
    0.50
    Act Density 0.059%

    No Known Activations