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

    Neuronpedia

    INDEX
    Explanations

    the closure of code blocks

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

    Code snippets and foreign words

    np_acts-logits-general · gemini-2.0-flash

    police officer / detection only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    انيف
    -0.58
    []
    -0.53
    ]:
    -0.51
     Bragg
    -0.51
    ',
    -0.51
    ()))
    -0.50
    。
    -0.50
    ))
    -0.48
    '):
    -0.48
     ver
    -0.48
    POSITIVE LOGITS
     fermés
    0.71
    tvguidetime
    0.71
     Audiodateien
    0.70
    Erreferentziak
    0.68
    ArgsConstructor
    0.65
     StatelessWidget
    0.65
    encodeWith
    0.65
     Exacts
    0.65
    GEBURTSDATUM
    0.64
     ujednoznacz
    0.64
    Act Density 0.018%

    No Known Activations