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

    Neuronpedia

    INDEX
    Explanations

    this [verb or noun phrase]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സര്‍
    0.50
     ਸਰ
    0.50
     സർ
    0.50
    gram
    0.47
    grant
    0.47
    openai
    0.46
    government
    0.46
    gène
    0.46
    productos
    0.46
    ທ່ານ
    0.45
    POSITIVE LOGITS
     Cindy
    0.54
     hoe
    0.49
     abstra
    0.49
     Rick
    0.47
     Sally
    0.47
     Guitar
    0.47
     recruiter
    0.46
     Name
    0.46
     County
    0.46
     guitar
    0.46
    Act Density 0.001%

    No Known Activations