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

    Neuronpedia

    INDEX
    Explanations

    historical and factual information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Topological
    0.36
     reducible
    0.32
     больных
    0.32
    ोलिक
    0.32
     Minimize
    0.32
     Minimal
    0.32
     minimal
    0.31
     Generals
    0.31
    Minimal
    0.31
    Ⲁ
    0.31
    POSITIVE LOGITS
     thursday
    0.47
    york
    0.45
    compan
    0.42
     didnt
    0.42
     zealand
    0.41
     saturday
    0.41
     england
    0.41
     wasnt
    0.41
    dozen
    0.41
    november
    0.41
    Act Density 0.000%

    No Known Activations