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

    Neuronpedia

    INDEX
    Explanations

    transform, augment, orchestrate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Row
    0.52
    Method
    0.50
     મારી
    0.49
    Cone
    0.48
    C
    0.47
    Re
    0.47
    College
    0.47
    Foods
    0.47
    Ral
    0.47
    Cho
    0.46
    POSITIVE LOGITS
     melindungi
    0.52
    él
    0.50
     reglamento
    0.48
     jouent
    0.48
     memudahkan
    0.46
     dispuesto
    0.46
    imine
    0.45
     habíamos
    0.45
     pakaian
    0.45
     glancing
    0.45
    Act Density 0.000%

    No Known Activations