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

    Neuronpedia

    INDEX
    Explanations

    equation query functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.21
    :
    0.21
     بتوان
    0.20
     کی۔
    0.20
    。
    0.20
    ):
    0.19
    ).
    0.19
     savent
    0.19
    ))
    0.18
    )).
    0.18
    POSITIVE LOGITS
     consists
    0.32
     are
    0.30
     includes
    0.30
     reflects
    0.29
     include
    0.28
     represents
    0.28
     serves
    0.28
     was
    0.27
     originated
    0.25
     originates
    0.25
    Act Density 2.141%

    No Known Activations