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

    Neuronpedia

    INDEX
    Explanations

    brackets and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rylic
    -0.07
     tác
    -0.06
     precip
    -0.06
    .getStringExtra
    -0.06
    اءات
    -0.06
     hatır
    -0.06
    拼
    -0.06
    _enemy
    -0.06
     отри
    -0.06
     někol
    -0.06
    POSITIVE LOGITS
     MACHINE
    0.07
    可
    0.07
     flawed
    0.07
    undle
    0.07
     Margin
    0.07
    ?",
    0.07
    系統
    0.07
    爵
    0.06
    	 ↵
    0.06
     drowning
    0.06
    Act Density 0.003%

    No Known Activations