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

    Neuronpedia

    INDEX
    Explanations

    commas or starts ideas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aime
    -0.07
    _trans
    -0.06
    <Block
    -0.06
    >");↵
    -0.06
    	DBG
    -0.06
    PasswordEncoder
    -0.06
    еня
    -0.06
     suspicious
    -0.06
     섬
    -0.06
     seedu
    -0.06
    POSITIVE LOGITS
    asset
    0.07
    qa
    0.07
     Elis
    0.07
    ritz
    0.07
     hearings
    0.06
     pays
    0.06
    웃
    0.06
     src
    0.06
    lararası
    0.06
    Posted
    0.06
    Act Density 0.161%

    No Known Activations