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

    Neuronpedia

    INDEX
    Explanations

    treasury or Trevor Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    رود
    0.46
    dtype
    0.45
    ある
    0.42
    ei
    0.40
    問題
    0.40
    ρι
    0.39
    evaluated
    0.39
    رس
    0.39
     Types
    0.38
    rau
    0.38
    POSITIVE LOGITS
     tre
    0.72
    Tre
    0.71
     Tre
    0.70
     TRE
    0.67
     тре
    0.66
    TRE
    0.65
     treasury
    0.64
    Treas
    0.64
     trove
    0.61
     Treasury
    0.59
    Act Density 0.006%

    No Known Activations