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

    Neuronpedia

    INDEX
    Explanations

    English sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifikasi
    -0.07
     повіт
    -0.07
    _home
    -0.06
     докум
    -0.06
    _probs
    -0.06
    关闭
    -0.06
    _cart
    -0.06
    imitive
    -0.06
    orous
    -0.06
     ancestors
    -0.06
    POSITIVE LOGITS
    ｜
    0.07
     hâlâ
    0.07
    0.07
     Mah
    0.07
     Они
    0.06
     kur
    0.06
    ιλ
    0.06
     lon
    0.06
     Sosyal
    0.06
    党
    0.06
    Act Density 0.067%
    No Known Activations