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

    Neuronpedia

    INDEX
    Explanations

    /*

    np_max-act · gemini-2.0-flash

    text related to software licensing and legal disclaimers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     спрос
    -0.07
     było
    -0.07
    wake
    -0.07
    áč
    -0.06
     Stop
    -0.06
     benöt
    -0.06
    ']))
    -0.06
     heights
    -0.06
     Gors
    -0.06
     nrows
    -0.06
    POSITIVE LOGITS
    +B
    0.07
     Jessica
    0.06
    .dw
    0.06
     Greatest
    0.06
    .high
    0.06
    .shape
    0.06
    ΙΟΥ
    0.06
    (.
    0.06
     Dav
    0.06
    .sm
    0.06
    Act Density 0.003%

    No Known Activations