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

    Neuronpedia

    INDEX
    Explanations

    system

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     energia
    -0.07
     futuro
    -0.07
    ágina
    -0.07
    뻑
    -0.07
    entialAction
    -0.07
    _Version
    -0.07
    ickt
    -0.07
     Außerdem
    -0.06
     Unsigned
    -0.06
    アメリ
    -0.06
    POSITIVE LOGITS
    _color
    0.08
    য
    0.07
    .disc
    0.07
     Morph
    0.07
    .pop
    0.07
    𝐶
    0.07
    ////////////////
    0.07
     swaps
    0.07
    �
    0.07
    	ok
    0.07
    Act Density 0.001%

    No Known Activations