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

    Neuronpedia

    INDEX
    Explanations

    offensive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    riften
    0.74
    sal
    0.72
    ewer
    0.70
     "'
    0.70
    oldt
    0.70
    shared
    0.69
    salary
    0.68
    datal
    0.68
    sms
    0.67
    uot
    0.67
    POSITIVE LOGITS
     cabbage
    0.86
    นี้
    0.85
     sfera
    0.80
     spowod
    0.80
     beetroot
    0.77
    Impossible
    0.77
     descarga
    0.77
     confid
    0.74
     wasteland
    0.74
     mercados
    0.73
    Act Density 0.007%

    No Known Activations