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

    Neuronpedia

    INDEX
    Explanations

    URLs, code, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ratio
    0.38
     bool
    0.35
     URI
    0.35
    omain
    0.35
     domain
    0.35
    iffent
    0.35
     /
    0.34
     기본
    0.34
    ests
    0.34
     җи
    0.34
    POSITIVE LOGITS
     originality
    0.54
    interesse
    0.43
     novelty
    0.41
    Lima
    0.40
     എഴു
    0.39
    Edu
    0.39
     Shipbuilding
    0.38
     araştırm
    0.38
    Lim
    0.38
     हितों
    0.38
    Act Density 0.005%

    No Known Activations