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

    Neuronpedia

    INDEX
    Explanations

    prominent names of individuals in various contexts

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

    male first names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kautta
    -0.60
     mukaan
    -0.58
    sividad
    -0.58
    ulement
    -0.57
     ilmo
    -0.57
     kiin
    -0.56
    parsedMessage
    -0.56
     AssemblyCompany
    -0.56
     vastaan
    -0.55
    IBOutlet
    -0.54
    POSITIVE LOGITS
     препратки
    0.45
     sage
    0.39
     vanilla
    0.38
     veal
    0.37
     "
    0.36
     foie
    0.36
     beef
    0.36
    apache
    0.36
    　　《
    0.35
     cuk
    0.35
    Act Density 0.046%

    No Known Activations