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

    Neuronpedia

    INDEX
    Explanations

    API-related commands and references

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

    API flows for clients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.63
    AndroidJUnit
    -0.59
    GTCX
    -0.59
    expandindo
    -0.59
     AssemblyProduct
    -0.56
    enderror
    -0.54
     Taktlose
    -0.51
    ))))))))
    -0.49
    RTCK
    -0.48
     Vikipedi
    -0.48
    POSITIVE LOGITS
     financieros
    0.38
     Hochzeit
    0.37
    urlaub
    0.36
     fehl
    0.36
    ự
    0.35
     deploy
    0.35
     eriş
    0.35
     TÉCN
    0.35
     democracia
    0.34
     vapa
    0.34
    Act Density 0.196%

    No Known Activations