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

    Neuronpedia

    INDEX
    Explanations

    technical library components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पोषक
    0.40
     مليون
    0.40
    <unused1038>
    0.38
     செல்க
    0.38
    욬
    0.38
    ativamente
    0.38
    饨
    0.38
    uce
    0.37
     पर्य
    0.37
    allenges
    0.37
    POSITIVE LOGITS
    Manager
    0.66
    AccessException
    0.55
    Factory
    0.55
    Builder
    0.54
    Exception
    0.50
    utils
    0.50
    Helper
    0.49
    Resolver
    0.48
     utils
    0.47
     manager
    0.47
    Act Density 0.020%

    No Known Activations