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

    Neuronpedia

    INDEX
    Explanations

    explanations or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suunn
    0.50
     permukaan
    0.46
    Tipo
    0.45
     서비스를
    0.45
    Plan
    0.43
     서비스
    0.43
    Hits
    0.43
    Visa
    0.42
    GET
    0.42
    Copies
    0.42
    POSITIVE LOGITS
     practical
    0.46
     discourses
    0.45
    结
    0.40
     critical
    0.39
     pondering
    0.39
     locus
    0.39
     consequential
    0.39
     burgeoning
    0.38
    ાળ
    0.38
     Practical
    0.38
    Act Density 0.005%

    No Known Activations