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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	port
    -0.07
    .ByteString
    -0.07
     Creation
    -0.06
    Tar
    -0.06
    sville
    -0.06
    elle
    -0.06
     Nikol
    -0.06
    が出
    -0.06
     WideString
    -0.06
    辺
    -0.06
    POSITIVE LOGITS
    وم
    0.07
    ++++
    0.06
    FAQ
    0.06
    действ
    0.06
     thoroughly
    0.06
    claim
    0.06
    コン
    0.06
    умент
    0.06
    ;%
    0.06
    ाइम
    0.06
    Act Density 0.039%

    No Known Activations