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

    Neuronpedia

    INDEX
    Explanations

    ip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grasp
    -0.08
    Verse
    -0.08
     clickable
    -0.08
    hes
    -0.07
     garoto
    -0.07
     শিশ
    -0.07
     ore
    -0.07
     ধারণ
    -0.07
     reiz
    -0.07
     হাতে
    -0.07
    POSITIVE LOGITS
     полит
    0.09
    政策
    0.08
     decorators
    0.08
    _policy
    0.07
    ಿನಲ್ಲಿ
    0.07
     Yam
    0.07
     coul
    0.07
     policies
    0.07
     политики
    0.07
     داخلی
    0.07
    Act Density 0.000%

    No Known Activations