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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heir
    -0.09
     byg
    -0.08
     وارد
    -0.08
     appartements
    -0.08
     Carter
    -0.08
     lect
    -0.08
     वाह
    -0.07
    فير
    -0.07
    Entering
    -0.07
    .sources
    -0.07
    POSITIVE LOGITS
     tags
    0.09
    ®
    0.08
     Tags
    0.08
     Pron
    0.08
    úng
    0.08
     Highway
    0.07
    -sidebar
    0.07
    _tags
    0.07
     Mania
    0.07
     phủ
    0.07
    Act Density 0.001%

    No Known Activations