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

    Neuronpedia

    INDEX
    Explanations

    at your own risk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sol
    0.74
    이랑
    0.65
     Overall
    0.65
     Max
    0.64
     Revolution
    0.64
     attualmente
    0.64
     Counting
    0.63
    avier
    0.63
    Guard
    0.63
     Surgery
    0.63
    POSITIVE LOGITS
     expense
    1.10
     cost
    1.09
     costo
    1.07
    成本
    1.04
    cost
    1.00
     coste
    1.00
     coût
    0.99
     inconvenience
    0.98
     비용
    0.95
     disconcert
    0.94
    Act Density 0.020%

    No Known Activations