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

    Neuronpedia

    INDEX
    Explanations

    derivative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fi
    -0.07
     cited
    -0.06
     dict
    -0.06
    (headers
    -0.06
     caste
    -0.06
    _approx
    -0.06
    厅
    -0.06
    _ix
    -0.06
     інозем
    -0.06
    (cam
    -0.06
    POSITIVE LOGITS
    hints
    0.07
    Alabama
    0.06
    gsub
    0.06
     نمای
    0.06
     przy
    0.06
    ximity
    0.06
    plement
    0.06
    urgery
    0.06
    ọn
    0.06
     základní
    0.06
    Act Density 0.001%

    No Known Activations