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

    Neuronpedia

    INDEX
    Explanations

    steps or process descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    az
    1.08
    osy
    1.02
     desenvolv
    1.00
    os
    0.98
    amas
    0.98
     जिनमें
    0.96
    é
    0.96
    restrict
    0.95
    ú
    0.95
    un
    0.95
    POSITIVE LOGITS
    流程
    1.76
    ขั้นตอน
    1.70
     steps
    1.63
     Processes
    1.53
     processes
    1.50
    Process
    1.45
    过程
    1.45
    過程
    1.45
     PROCESS
    1.43
     Process
    1.41
    Act Density 0.698%

    No Known Activations