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

    Neuronpedia

    INDEX
    Explanations

    connections and associations within various contexts

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

    line or defects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //--
    -0.27
    "
    -0.23
    ///
    -0.22
    —
    -0.20
    //
    -0.20
        
    -0.20
    #
    -0.20
    “
    -0.20
    ―
    -0.19
    </em>
    -0.19
    POSITIVE LOGITS
     témoig
    0.93
     queſto
    0.91
    <unused74>
    0.90
    <unused14>
    0.90
    <unused3>
    0.90
    [@BOS@]
    0.90
    <unused8>
    0.90
    <unused52>
    0.90
    <pad>
    0.89
    <unused16>
    0.89
    Act Density 0.083%

    No Known Activations