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

    Neuronpedia

    INDEX
    Explanations

    first step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">>
    0.39
    वि
    0.38
     отста
    0.37
    ୫
    0.36
     硬
    0.35
    )"><
    0.35
    Celeron
    0.35
     Pipelines
    0.35
    唝
    0.34
    ]>
    0.34
    POSITIVE LOGITS
     putting
    0.49
     closer
    0.44
    putting
    0.44
    stepping
    0.44
     put
    0.42
     stepping
    0.42
     pok
    0.41
    closer
    0.40
     Step
    0.40
     وهو
    0.40
    Act Density 0.000%

    No Known Activations