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

    Neuronpedia

    INDEX
    Explanations

    qualifiers related to the strength or type of attributes in code definitions

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

    shorten edge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    səhifə
    -0.84
     beginnetje
    -0.69
     виправивши
    -0.68
    GraphicsUnit
    -0.67
     queſta
    -0.66
    Tikang
    -0.66
    verwijspagina
    -0.65
    messageInfo
    -0.65
     AllAfrica
    -0.65
     betweenstory
    -0.64
    POSITIVE LOGITS
     strong
    0.47
     Strong
    0.38
    strong
    0.37
    Strong
    0.37
     prisa
    0.36
     asamblea
    0.35
    NotNull
    0.35
     tunggal
    0.34
    NonNull
    0.34
     serpiente
    0.34
    Act Density 0.001%

    No Known Activations