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

    Neuronpedia

    INDEX
    Explanations

    computer code and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.41
     quadr
    0.39
     silos
    0.36
     firewall
    0.36
     elements
    0.35
     sheen
    0.35
    0.35
     burden
    0.35
     sham
    0.35
     meridian
    0.34
    POSITIVE LOGITS
    Tonight
    0.41
    Deleting
    0.40
    当我
    0.39
    揩
    0.39
    Want
    0.39
    Everyone
    0.38
     করল
    0.38
    हमने
    0.38
    䊂
    0.38
    শুক্রবার
    0.38
    Act Density 0.000%

    No Known Activations