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

    Neuronpedia

    INDEX
    Explanations

    references to authors and contributors in research or academic papers

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

    initials and coded references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distinct
    -0.49
     evolution
    -0.45
     evolving
    -0.45
     Evolution
    -0.45
    hyper
    -0.44
    ophilus
    -0.44
    гід
    -0.43
    isław
    -0.43
    evolution
    -0.43
    mut
    -0.42
    POSITIVE LOGITS
    Cyfeiriadau
    0.62
    SharedDtor
    0.48
     للمعارف
    0.47
     ujednoznacz
    0.46
     Photocase
    0.46
    Зноскі
    0.45
    RegressionTest
    0.43
     Administrativna
    0.43
    MathML
    0.42
     hjemmeside
    0.41
    Act Density 0.617%

    No Known Activations