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

    Neuronpedia

    INDEX
    Explanations

    ner, Excel, body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    1.76
    .
    1.52
     this
    1.45
     that
    1.41
    ".
    1.32
     it
    1.30
    ",
    1.30
     the
    1.30
    !
    1.30
    ."
    1.18
    POSITIVE LOGITS
    remeno
    1.16
    utory
    1.13
    щает
    1.05
    istra
    1.01
    Με
    1.00
    ungkinkan
    1.00
     utilizó
    0.98
    妛
    0.98
    ផ្តល់
    0.98
     একটি
    0.96
    Act Density 0.236%

    No Known Activations