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

    Neuronpedia

    INDEX
    Explanations

    a summary or breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     experimenting
    0.61
    ങ്ങളിലും
    0.60
     ngờ
    0.56
    InputValue
    0.55
    velope
    0.55
    ngthening
    0.55
     sostitu
    0.54
    Mutable
    0.54
    更换
    0.54
    を発
    0.54
    POSITIVE LOGITS
     summary
    2.81
     overview
    2.51
    summary
    2.50
     summaries
    2.42
    Summary
    2.38
     Summary
    2.36
     summarize
    2.18
     Overview
    2.10
     summarized
    2.08
     resumen
    2.06
    Act Density 2.982%

    No Known Activations