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

    Neuronpedia

    INDEX
    Explanations

    keywords related to notable achievements and performance evaluations

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

    you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gardes
    -0.33
     garde
    -0.28
     trust
    -0.28
     общество
    -0.28
    ablon
    -0.27
    пьютер
    -0.25
    eseorang
    -0.25
     cater
    -0.24
     sombra
    -0.24
    Mine
    -0.24
    POSITIVE LOGITS
    tonode
    0.82
    Попис
    0.78
     <<<<<<<<<<<<<<
    0.77
    ValueStyle
    0.69
     Мексичка
    0.69
    msgTypes
    0.66
     препратки
    0.66
     Administrativna
    0.63
    stdc
    0.63
    MemoryWarning
    0.62
    Act Density 0.247%

    No Known Activations