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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rectangle
    -0.07
     kingdoms
    -0.07
     addTo
    -0.06
     UIManager
    -0.06
     Lily
    -0.06
     makin
    -0.06
    acılık
    -0.06
     exemplary
    -0.06
    architecture
    -0.06
     Initially
    -0.06
    POSITIVE LOGITS
    selling
    0.06
    ΟΡ
    0.06
     معت
    0.06
     №
    0.06
     ölçü
    0.06
    某
    0.06
     jacket
    0.06
    iae
    0.06
    .Guid
    0.06
     Серед
    0.06
    Act Density 0.029%

    No Known Activations