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

    Neuronpedia

    INDEX
    Explanations

    error encountered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Shoes
    0.79
    Ratio
    0.69
    Ve
    0.69
    Chk
    0.69
    ວນ
    0.66
     geï
    0.66
    Doors
    0.66
    typically
    0.65
    icularly
    0.65
    эффици
    0.64
    POSITIVE LOGITS
     technical
    0.95
     техни
    0.80
     तकनीकी
    0.77
     технических
    0.77
     ಸ್ವಲ್ಪ
    0.76
     server
    0.76
     Technical
    0.75
     unexpected
    0.74
     tecn
    0.72
    一點
    0.72
    Act Density 0.000%

    No Known Activations