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

    Neuronpedia

    INDEX
    Explanations

    URLs containing https

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Clap
    0.74
     employee
    0.73
    च्‍
    0.71
     employees
    0.66
     পাওয়
    0.65
    储存
    0.64
     تس
    0.62
     ఇం
    0.61
     تاب
    0.61
    دا
    0.61
    POSITIVE LOGITS
     фрон
    0.86
     frontend
    0.82
    frontal
    0.80
    linien
    0.80
    classifier
    0.79
     महाराज
    0.79
     фара
    0.75
     cues
    0.75
    front
    0.75
     front
    0.75
    Act Density 0.009%

    No Known Activations