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

    Neuronpedia

    INDEX
    Explanations

    `:` and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verme
    0.46
     patip
    0.38
     úspě
    0.38
    გნ
    0.38
     discriminating
    0.38
    󠁴
    0.38
    ển
    0.38
    ഗോ
    0.38
    識
    0.38
     forego
    0.37
    POSITIVE LOGITS
    developer
    0.39
     proven
    0.37
     dozens
    0.37
    gling
    0.36
    indle
    0.36
    developers
    0.36
    NASDAQ
    0.35
     developers
    0.34
     turbines
    0.34
     Lost
    0.34
    Act Density 0.000%

    No Known Activations