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

    Neuronpedia

    INDEX
    Explanations

    General English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    щается
    -0.07
    pq
    -0.06
    upport
    -0.06
    patients
    -0.06
    Handles
    -0.06
     nghiệp
    -0.06
    emoc
    -0.06
     expressly
    -0.06
     righteous
    -0.06
    PROJECT
    -0.06
    POSITIVE LOGITS
    oundingBox
    0.07
    mean
    0.07
    _LSB
    0.07
     пов
    0.06
    잖
    0.06
    awa
    0.06
    imp
    0.06
     sculptures
    0.06
     tidak
    0.06
     sculpture
    0.06
    Act Density 0.235%

    No Known Activations