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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ório
    -0.08
     chests
    -0.08
     vested
    -0.07
    �부
    -0.07
    ọng
    -0.07
     imagem
    -0.06
    bitset
    -0.06
     性
    -0.06
    �
    -0.06
     cottage
    -0.06
    POSITIVE LOGITS
     Gates
    0.07
     elusive
    0.06
     Background
    0.06
    TA
    0.06
    巴
    0.06
    ***/↵↵
    0.06
     markdown
    0.06
     COLOR
    0.06
    unciation
    0.06
    effective
    0.06
    Act Density 0.000%

    No Known Activations