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

    Neuronpedia

    INDEX
    Explanations

    elements related to legal terms and conditions, particularly within software licenses

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

    FOR A PARTICULAR PURPOSE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.27
     E
    -0.25
    <eos>
    -0.25
    8
    -0.24
     T
    -0.24
     
    -0.24
    4
    -0.24
    2
    -0.24
    ,
    -0.24
    ma
    -0.23
    POSITIVE LOGITS
     queſto
    0.94
    ſammen
    0.93
     zwiſchen
    0.92
     zuſammen
    0.91
     imagui
    0.90
    ſelben
    0.88
     queſta
    0.87
    <unused41>
    0.87
    <unused28>
    0.87
    [@BOS@]
    0.87
    Act Density 0.135%

    No Known Activations