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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.51
     I
    0.47
     `
    0.47
    u
    0.47
     Like
    0.46
    '
    0.46
     \
    0.45
     U
    0.45
     Alex
    0.45
    i
    0.45
    POSITIVE LOGITS
    <0x99>
    0.55
     adhipp
    0.53
    <0xAC>
    0.52
    <0x92>
    0.52
    <0x97>
    0.52
    <0x9B>
    0.52
    GALAD
    0.51
    <0x91>
    0.50
    <0x95>
    0.50
    <0xAB>
    0.49
    Act Density 0.001%

    No Known Activations