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

    Neuronpedia

    INDEX
    Explanations

    financial fraud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Duty
    0.41
    ICK
    0.40
    Later
    0.39
    weekly
    0.39
     너무
    0.39
    Grass
    0.39
    യിലും
    0.38
     grass
    0.38
     옆
    0.37
     grassy
    0.37
    POSITIVE LOGITS
     एन
    0.42
     infestation
    0.41
    чена
    0.40
    சென்னை
    0.37
     Associate
    0.37
     ux
    0.37
     Spinner
    0.36
     regress
    0.36
     Infinite
    0.36
     donations
    0.36
    Act Density 0.000%

    No Known Activations