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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sectors
    -0.07
     بالا
    -0.07
     NEXT
    -0.07
    /home
    -0.07
     sayesinde
    -0.06
    莉
    -0.06
     objetivo
    -0.06
     bending
    -0.06
    Over
    -0.06
    (hidden
    -0.06
    POSITIVE LOGITS
     worst
    0.08
    _assigned
    0.07
     antim
    0.06
     worsening
    0.06
    lun
    0.06
     Worst
    0.06
     useParams
    0.06
     кін
    0.06
    ск
    0.06
     stringWithFormat
    0.06
    Act Density 0.035%

    No Known Activations