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

    Neuronpedia

    INDEX
    Explanations

    T5 variants and MBART

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.58
     thick
    0.48
     Jamal
    0.47
     Understanding
    0.47
     Ensuring
    0.47
     AER
    0.46
     a
    0.46
     AB
    0.46
     Refining
    0.46
     Determining
    0.45
    POSITIVE LOGITS
    ﺓ
    0.51
    organizzazione
    0.50
    iciones
    0.49
     müşter
    0.49
    вые
    0.48
    preco
    0.48
    ные
    0.47
    łączy
    0.47
    zovaniyu
    0.46
    żą
    0.46
    Act Density 0.006%

    No Known Activations