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

    Neuronpedia

    INDEX
    Explanations

    titles preceding names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Type
    0.31
     heatmap
    0.30
    Size
    0.30
    💡
    0.30
     Chromebook
    0.30
     convoluted
    0.30
     HTML
    0.29
    மைப்பு
    0.29
     DDoS
    0.29
     natively
    0.29
    POSITIVE LOGITS
     John
    0.54
     William
    0.53
     Joseph
    0.52
     Robert
    0.49
     Richard
    0.49
     George
    0.49
     James
    0.48
     Jonathan
    0.47
     Michael
    0.46
     Mike
    0.46
    Act Density 0.160%

    No Known Activations