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

    Neuronpedia

    INDEX
    Explanations

    Science and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Atomic
    -0.74
    Atomic
    -0.71
    Translation
    -0.67
     Translation
    -0.62
     atomic
    -0.60
    enchymal
    -0.59
    ouching
    -0.57
    atomic
    -0.56
    runchy
    -0.54
    BagConstraints
    -0.54
    POSITIVE LOGITS
     Normdatei
    0.60
    Personendaten
    0.58
    ReusableCell
    0.58
     OnInit
    0.54
    ModelAdmin
    0.54
     CreateTagHelper
    0.52
    رشف
    0.52
     wireType
    0.52
    ########.
    0.51
    ally
    0.50
    Act Density 0.018%

    No Known Activations