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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ortex
    -0.07
     theolog
    -0.07
    ovanou
    -0.07
     recess
    -0.07
    380
    -0.06
    _footer
    -0.06
     工
    -0.06
     modest
    -0.06
    501
    -0.06
     position
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ::|
    0.07
    ='',
    0.06
    爱
    0.06
    Newsletter
    0.06
    ALK
    0.06
     Kế
    0.06
     müş
    0.06
    Subscriber
    0.06
     ngại
    0.06
    Act Density 0.005%

    No Known Activations