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

    Neuronpedia

    INDEX
    Explanations

    risks everything, incoming call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шие
    0.49
     navigateur
    0.47
    л
    0.47
    粡
    0.47
    ﻟ
    0.46
    鏘
    0.45
     montant
    0.45
    განიზ
    0.45
     createState
    0.44
     plaid
    0.44
    POSITIVE LOGITS
    ayn
    0.52
     অন্যান্য
    0.49
    äne
    0.48
    NR
    0.46
     starten
    0.46
    RecordPtr
    0.46
    awab
    0.45
    Hy
    0.44
    ainya
    0.44
    }.$$
    0.44
    Act Density 0.001%

    No Known Activations