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

    Neuronpedia

    INDEX
    Explanations

    teaching methods, assistant, philosophy, tolerance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Alipay
    0.43
     sauce
    0.40
     bees
    0.40
     rules
    0.40
    ستانی
    0.39
     Rules
    0.38
    onRequest
    0.38
     பட்டிய
    0.38
    Lists
    0.37
     swallow
    0.37
    POSITIVE LOGITS
     ଭ
    0.46
     assistants
    0.43
     assistant
    0.43
    learning
    0.42
     Assistants
    0.41
    Assistant
    0.40
    assistant
    0.40
    Learning
    0.39
     style
    0.38
    kv
    0.38
    Act Density 0.003%

    No Known Activations