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

    Neuronpedia

    INDEX
    Explanations

    terms related to software components or data structures in programming

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

    adapter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <u>
    -0.41
      
    -0.41
    The
    -0.40
    Gro
    -0.39
                                   
    -0.38
    <sup>
    -0.38
    <i>
    -0.38
    '
    -0.37
    <b>
    -0.37
     HNO
    -0.37
    POSITIVE LOGITS
    Adapter
    1.81
     Adapter
    1.76
     adapter
    1.70
    adapter
    1.67
     adapters
    1.60
    adapters
    1.48
    Adapters
    1.38
     Adap
    1.34
    getAdapter
    1.30
     Adaptation
    1.24
    Act Density 0.010%

    No Known Activations