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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ّه
    -0.08
    ת
    -0.07
    립니다
    -0.07
     distribu
    -0.07
    �
    -0.07
    引
    -0.07
    mektedir
    -0.07
    bv
    -0.07
    _TYPED
    -0.07
    慈
    -0.07
    POSITIVE LOGITS
     ×
    0.10
     ઉપરાંત
    0.09
     ಜೊತೆ
    0.08
     સાથે
    0.08
     +
    0.08
     combinación
    0.08
    ებთან
    0.08
     ಜೊ
    0.08
    Race
    0.08
     белән
    0.08
    Act Density 0.250%

    No Known Activations