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

    Neuronpedia

    INDEX
    Explanations

    did or initWith structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.76
     sedative
    0.73
     tsunami
    0.71
     substandard
    0.69
     curative
    0.66
     substant
    0.66
     criminal
    0.65
     abhor
    0.64
     всей
    0.64
     narcotic
    0.64
    POSITIVE LOGITS
    ，
    0.75
    נו
    0.69
    จะ
    0.66
    <0xA2>
    0.63
    ני
    0.61
    =>{
    0.61
    '
    0.61
    -
    0.61
    し
    0.57
    ote
    0.54
    Act Density 0.000%

    No Known Activations