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

    Neuronpedia

    INDEX
    Explanations

    poverty and global challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.50
     is
    0.47
    ۔
    0.47
     it
    0.46
     ді
    0.44
    ní
    0.43
     violência
    0.43
     م
    0.42
    ش
    0.42
     mesmas
    0.42
    POSITIVE LOGITS
    i
    0.76
    an
    0.73
    -
    0.70
    n
    0.64
    н
    0.62
    at
    0.61
    el
    0.54
    י
    0.51
    L
    0.50
    <0x80>
    0.48
    Act Density 0.001%

    No Known Activations