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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Holocaust
    -0.07
    ⻁
    -0.07
     från
    -0.07
     verr
    -0.07
    カン
    -0.07
    就说
    -0.07
     voor
    -0.07
    第二届
    -0.07
    Ґ
    -0.07
    POSITIVE LOGITS
     LUA
    0.07
     mente
    0.07
    '>↵↵
    0.07
     mudança
    0.07
    Leaks
    0.07
    📛
    0.06
    伝え
    0.06
    SHORT
    0.06
     chave
    0.06
    :UIControlEvent
    0.06
    Act Density 0.104%

    No Known Activations