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

    Neuronpedia

    INDEX
    Explanations

    insider trading and market manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    くい
    0.40
    Wilson
    0.40
    ிகி
    0.37
    Abd
    0.37
    tDBOutput
    0.36
    作用
    0.36
    тили
    0.36
     Pass
    0.36
    麓
    0.36
    鍔
    0.36
    POSITIVE LOGITS
     Jupiter
    0.62
     theft
    0.59
    Jupiter
    0.58
     J
    0.54
    盜
    0.54
    盗
    0.54
     steals
    0.53
     stole
    0.53
     thefts
    0.52
     steal
    0.51
    Act Density 0.000%

    No Known Activations