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

    Neuronpedia

    INDEX
    Explanations

    dial followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AGR
    0.38
     Unlimited
    0.37
    飛
    0.37
    Tomorrow
    0.37
     yık
    0.37
     الاجتماعي
    0.36
     Asp
    0.35
    opol
    0.35
     Rg
    0.35
    Unlimited
    0.34
    POSITIVE LOGITS
     discret
    0.40
    ischem
    0.38
    dataPro
    0.37
    坑
    0.36
    allel
    0.36
     pid
    0.35
     discreet
    0.35
     discretized
    0.34
     dedu
    0.34
    стый
    0.33
    Act Density 0.004%

    No Known Activations