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

    Neuronpedia

    INDEX
    Explanations

    correction chart, species, India

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ihr
    0.44
     produced
    0.41
     purs
    0.41
     production
    0.40
     hunk
    0.40
     global
    0.40
     производи
    0.40
     упо
    0.40
     think
    0.39
    произ
    0.39
    POSITIVE LOGITS
    ↴
    0.40
     लैस
    0.40
    Marc
    0.39
     RICO
    0.38
    addColorStop
    0.38
    Quiet
    0.38
    replacement
    0.38
    矯
    0.37
    บู
    0.36
    Disconnect
    0.36
    Act Density 0.001%

    No Known Activations