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

    Neuronpedia

    INDEX
    Explanations

    failure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ç
    -0.07
     nějaké
    -0.07
     lub
    -0.07
     trưng
    -0.07
     resourceId
    -0.07
     Brighton
    -0.06
     boring
    -0.06
    aln
    -0.06
     phi
    -0.06
     블
    -0.06
    POSITIVE LOGITS
     failure
    0.18
     Failure
    0.13
    ailure
    0.11
     FAILURE
    0.11
     HF
    0.08
    failure
    0.07
     работа
    0.07
     людина
    0.06
    <|begin_of_text|>
    0.06
     подготов
    0.06
    Act Density 0.005%

    No Known Activations