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

    Neuronpedia

    INDEX
    Explanations

    saying yes or no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بالضبط
    0.40
    াজিক
    0.37
    اديم
    0.35
    ^+
    0.34
     Leopard
    0.34
     Panic
    0.34
    mazon
    0.34
     sacked
    0.33
     Transcription
    0.33
     Blitz
    0.33
    POSITIVE LOGITS
     buts
    0.74
     YES
    0.65
     WHERE
    0.64
    YES
    0.62
     ‘
    0.61
     WHEN
    0.61
    WHERE
    0.60
    WHEN
    0.60
     Maybe
    0.59
     THERE
    0.59
    Act Density 0.163%

    No Known Activations