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
    /N
    -0.07
    価
    -0.07
     Fuj
    -0.07
    ی
    -0.07
    _Node
    -0.07
     slash
    -0.06
     Foo
    -0.06
     Symphony
    -0.06
    ρια
    -0.06
    ysi
    -0.06
    POSITIVE LOGITS
    ativos
    0.07
     arrivals
    0.07
     сор
    0.07
    ---↵↵
    0.06
    .....
    0.06
    	DB
    0.06
    --------↵↵
    0.06
     activists
    0.06
     ارتباط
    0.06
     yaşında
    0.06
    Act Density 0.002%

    No Known Activations