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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riterion
    -0.07
    ken
    -0.07
     Perkins
    -0.06
     tỏ
    -0.06
    _placement
    -0.06
     pageInfo
    -0.06
     '}↵
    -0.06
    Streamer
    -0.06
     tận
    -0.06
     факти
    -0.06
    POSITIVE LOGITS
    setBackground
    0.07
    :P
    0.07
    سة
    0.06
     Особ
    0.06
     Especially
    0.06
     лич
    0.06
     suchen
    0.06
    étique
    0.06
     вис
    0.06
    价
    0.06
    Act Density 0.021%

    No Known Activations