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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idential
    -0.06
     Phó
    -0.06
    .“↵↵
    -0.06
    Add
    -0.06
     Applies
    -0.06
     tangible
    -0.06
     rotates
    -0.06
     duct
    -0.06
    큼
    -0.06
     чувств
    -0.06
    POSITIVE LOGITS
    dep
    0.07
     книги
    0.06
    orthand
    0.06
     तरफ
    0.06
     Ricardo
    0.06
    Curr
    0.06
     firsthand
    0.06
     tzv
    0.06
    .pay
    0.06
    lesai
    0.06
    Act Density 0.022%

    No Known Activations