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

    Neuronpedia

    INDEX
    Explanations

    nouns and verbs related to actions or descriptions in a specific context

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

    akan, akan, Japanese, kan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arangay
    -0.63
    ckså
    -0.54
    Koordinaten
    -0.47
    enyum
    -0.45
    Eloquent
    -0.45
    anggung
    -0.45
    PageFactory
    -0.44
    Rhythm
    -0.42
    yszer
    -0.42
    bufio
    -0.42
    POSITIVE LOGITS
     Autorizaciones
    0.55
     Italijanski
    0.49
     Japanese
    0.48
    ERICAN
    0.47
    akan
    0.47
     تكبرها
    0.47
     "%"
    0.46
    katan
    0.46
    AKAN
    0.44
     japanese
    0.44
    Act Density 0.001%

    No Known Activations