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

    Neuronpedia

    INDEX
    Explanations

    things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     smothered
    0.41
     idealism
    0.39
     confined
    0.39
    igg
    0.38
    twice
    0.38
     overboard
    0.38
    ণ
    0.37
    ckers
    0.37
     infinitesimal
    0.37
     lin
    0.36
    POSITIVE LOGITS
     afili
    0.50
     verão
    0.50
     coisas
    0.50
    Runtime
    0.49
     cartão
    0.47
     seharusnya
    0.47
     qualquer
    0.46
    Slash
    0.46
     serviços
    0.46
     çalış
    0.46
    Act Density 0.002%

    No Known Activations