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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical notation and equations

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

    Mathematical notation/formula

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    новништво
    -0.63
    \<^
    -0.61
     OMITBAD
    -0.61
     hObject
    -0.61
     RouterModule
    -0.60
    ⃣
    -0.60
    !&
    -0.59
     himo
    -0.59
    raba
    -0.58
    /-/
    -0.58
    POSITIVE LOGITS
     where
    0.76
    。
    0.65
    .
    0.65
     which
    0.62
    }}},
    0.61
    ),
    0.61
    where
    0.61
    ))),
    0.59
     whereas
    0.59
    =:
    0.58
    Act Density 1.914%

    No Known Activations