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

    Neuronpedia

    INDEX
    Explanations

    structure learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .**
    0.61
    .​​
    0.57
    .​
    0.54
    .+
    0.54
    .")
    0.50
    espèce
    0.50
    .[/
    0.50
    >):
    0.49
    0.49
    .
    0.49
    POSITIVE LOGITS
     Traverse
    0.46
     Hearing
    0.43
     Embro
    0.42
     Guide
    0.41
    只有
    0.41
     Coulomb
    0.41
     Schulz
    0.41
     Health
    0.40
     Memorandum
    0.40
     nation
    0.39
    Act Density 0.002%

    No Known Activations