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

    Neuronpedia

    INDEX
    Explanations

    reverse proxy evaluating SQL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.58
    ett
    0.54
    cover
    0.54
    ated
    0.53
    Al
    0.53
    is
    0.51
    holt
    0.51
    wa
    0.51
    í
    0.51
    5
    0.50
    POSITIVE LOGITS
     конф
    0.52
     inglese
    0.52
     esforços
    0.52
     utilizzo
    0.51
    ایہ
    0.51
     отличи
    0.51
     đức
    0.49
     핵심
    0.49
     አመ
    0.48
     ничек
    0.48
    Act Density 0.000%

    No Known Activations