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

    Neuronpedia

    INDEX
    Explanations

    Boromir, these, this scenario

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    0.59
    j
    0.52
    z
    0.50
    قبال
    0.45
    more
    0.45
     syndromes
    0.44
    sett
    0.44
    អ្វី
    0.43
    amiento
    0.42
     huv
    0.42
    POSITIVE LOGITS
    柽
    0.48
     compat
    0.46
     Là
    0.45
     هستیم
    0.45
    OTA
    0.45
     spiced
    0.45
    沺
    0.44
    Само
    0.44
    ilan
    0.42
    את
    0.42
    Act Density 0.003%

    No Known Activations