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

    Neuronpedia

    INDEX
    Explanations

    possibilities and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smothered
    0.54
    ר
    0.52
    ять
    0.50
     unchecked
    0.48
     millionaire
    0.48
    不
    0.48
     deft
    0.47
     duckys
    0.46
    reat
    0.46
    ו
    0.45
    POSITIVE LOGITS
    și
    0.48
     Lei
    0.47
    țele
    0.46
     গ
    0.46
     kø
    0.45
     Ray
    0.43
    Ports
    0.43
     আলোকে
    0.43
     एमसीक्यू
    0.43
     ray
    0.43
    Act Density 0.000%

    No Known Activations