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

    Neuronpedia

    INDEX
    Explanations

    specific combination or substance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    讶
    0.45
    皖
    0.45
     ஆகியவை
    0.44
    SNR
    0.43
    STRAL
    0.43
    quate
    0.43
     dagar
    0.43
     cautions
    0.42
    มาณ
    0.42
    𒌓
    0.42
    POSITIVE LOGITS
    ر
    0.52
    is
    0.44
     explosion
    0.42
    doesn
    0.41
     شد
    0.40
    цо
    0.40
    桦
    0.40
     easier
    0.39
    jede
    0.39
    ikus
    0.39
    Act Density 0.000%

    No Known Activations