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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that refer to location

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ècie
    -0.68
     дописавши
    -0.65
    awtextra
    -0.63
    $_['
    -0.59
    RTEX
    -0.55
    NameInMap
    -0.53
    -0.50
    (&:
    -0.47
     Réponses
    -0.47
    Autoritní
    -0.47
    POSITIVE LOGITS
    resave
    0.58
     høre
    0.54
     scolaires
    0.54
     deberes
    0.53
     sauvage
    0.53
     corrientes
    0.52
     Marlow
    0.52
     chré
    0.52
     régulier
    0.52
     toscana
    0.51
    Act Density 5.566%

    No Known Activations