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

    Neuronpedia

    INDEX
    Explanations

    philosophical/theoretical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expects
    -0.08
     aspect
    -0.07
     acess
    -0.07
     phosph
    -0.07
    $wp
    -0.07
    裨
    -0.07
     kinds
    -0.07
    essaging
    -0.06
     clarify
    -0.06
     broadcasting
    -0.06
    POSITIVE LOGITS
     исследования
    0.08
    表现出
    0.07
     winds
    0.07
    Body
    0.07
    transaction
    0.07
    奋战
    0.07
    ین
    0.07
     sailors
    0.07
    إصابة
    0.07
    ingle
    0.07
    Act Density 0.097%

    No Known Activations