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

    Neuronpedia

    INDEX
    Explanations

    connections or relationships expressed through prepositions and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    FIGS or legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.93
     Chriftian
    -0.89
     Monfieur
    -0.87
     noastră
    -0.85
     pleaſure
    -0.85
     Majefty
    -0.84
     Jefus
    -0.84
     themſelves
    -0.83
     myſelf
    -0.82
     raiſ
    -0.81
    POSITIVE LOGITS
     final
    0.64
    ordinates
    0.63
     ab
    0.63
    )<<
    0.62
     za
    0.61
    ardar
    0.60
     cu
    0.59
     hin
    0.58
    |}{\
    0.58
     Er
    0.58
    Act Density 0.019%

    No Known Activations