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

    Neuronpedia

    INDEX
    Explanations

    object

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    embr
    0.72
    demos
    0.63
     गिरफ्त
    0.61
    odendron
    0.60
    odian
    0.60
    Apache
    0.60
    emo
    0.59
    見
    0.58
     bikin
    0.58
    เต็ม
    0.58
    POSITIVE LOGITS
     object
    0.84
     objects
    0.83
     estime
    0.76
     എന്നാണ്
    0.75
    object
    0.74
     acredita
    0.73
     对象
    0.71
    ابل
    0.69
    对象
    0.69
     élevées
    0.69
    Act Density 0.001%

    No Known Activations