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

    Neuronpedia

    INDEX
    Explanations

    Get stream

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berpeng
    0.40
    льные
    0.39
     Boden
    0.38
     Lad
    0.37
     Tail
    0.37
     perl
    0.37
     Sl
    0.37
    ρίζ
    0.37
     Bubble
    0.36
     鳥
    0.36
    POSITIVE LOGITS
    Hosted
    0.43
    hc
    0.42
     ipotesi
    0.41
     Hosted
    0.39
    Hosting
    0.39
     हाईकोर्ट
    0.38
    FileVersion
    0.38
    vely
    0.37
     repatri
    0.37
     होस्ट
    0.37
    Act Density 0.056%

    No Known Activations