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

    Neuronpedia

    INDEX
    Explanations

    colons and numerical specifications

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

    MDF, new, red

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.68
     дописавши
    -0.66
     yym
    -0.64
     Савезне
    -0.59
     ProtoMessage
    -0.56
     gyhoeddwyd
    -0.56
     nahilalakip
    -0.55
    NameInMap
    -0.53
    SourceChecksum
    -0.52
    сылкі
    -0.52
    POSITIVE LOGITS
    省市镇
    0.41
    الدراسه
    0.40
    setVerticalGroup
    0.40
     mostly
    0.39
     a
    0.36
    チール
    0.35
     finos
    0.34
     primarily
    0.34
     mainly
    0.33
     finas
    0.33
    Act Density 0.005%

    No Known Activations