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

    Neuronpedia

    INDEX
    Explanations

    code generation and prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intelligente
    0.32
     inim
    0.31
    साम
    0.31
     psychos
    0.31
     yönet
    0.30
     terren
    0.30
     difficiles
    0.30
     intelligents
    0.30
     horrors
    0.30
     эмоциона
    0.30
    POSITIVE LOGITS
     Publisher
    0.31
    onCreate
    0.29
    OnInit
    0.29
     ((
    0.28
     one
    0.28
     new
    0.27
     One
    0.27
    已
    0.27
     Garage
    0.26
     (:
    0.26
    Act Density 0.112%

    No Known Activations