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

    Neuronpedia

    INDEX
    Explanations

    different starting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    0.23
     (
    0.23
     _
    0.23
     to
    0.22
     applicable
    0.22
     *
    0.22
     -->
    0.22
     ھ
    0.21
     Table
    0.21
     colds
    0.21
    POSITIVE LOGITS
    <unused1864>
    0.24
    어진
    0.24
    <unused226>
    0.24
    <unused511>
    0.24
    <unused338>
    0.23
    ле
    0.23
    אי
    0.22
    <unused428>
    0.22
    <unused432>
    0.22
    у
    0.22
    Act Density 1.354%

    No Known Activations