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

    Neuronpedia

    INDEX
    Explanations

    reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    0.55
    ton
    0.50
    co
    0.48
    gaz
    0.47
    k
    0.47
    n
    0.46
    ia
    0.46
    dock
    0.46
    g
    0.46
    v
    0.45
    POSITIVE LOGITS
     sanitizer
    0.51
     হাসপাত
    0.46
     प्रस्ताव
    0.45
    ๋ยว
    0.44
    쯜
    0.44
    బర్
    0.44
    плення
    0.44
     τρί
    0.44
     userdata
    0.44
    ↡
    0.44
    Act Density 0.000%

    No Known Activations