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

    Neuronpedia

    INDEX
    Explanations

    will be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anks
    0.27
    ?
    0.26
    ны
    0.26
    ？
    0.24
    ↵
    0.24
     analyzers
    0.24
     Drives
    0.24
    ’
    0.24
     breaths
    0.24
     Doesn
    0.23
    POSITIVE LOGITS
     have
    0.38
     be
    0.35
     nevoie
    0.33
    have
    0.33
     necesitar
    0.33
     иметь
    0.32
     probablement
    0.30
     need
    0.30
     تحتاج
    0.30
     deberá
    0.29
    Act Density 0.506%

    No Known Activations