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

    Neuronpedia

    INDEX
    Explanations

    people who care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    people
    0.79
    Our
    0.78
     humans
    0.75
     involving
    0.72
     people
    0.71
     using
    0.71
     preferring
    0.70
     accruing
    0.68
     raconte
    0.68
     extracting
    0.67
    POSITIVE LOGITS
     তারাও
    0.77
     পারেনা
    0.74
    ट्टर
    0.74
     Volumen
    0.74
    இத
    0.71
    isee
    0.70
     спеціа
    0.69
    स्पीड
    0.69
     পায়নি
    0.67
    ahui
    0.67
    Act Density 0.073%

    No Known Activations