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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or superlatives

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

    most adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.39
     propOrder
    -0.36
    ništ
    -0.36
     órganos
    -0.35
    ähteet
    -0.35
    ungsver
    -0.34
     Wahr
    -0.33
    ConverterFactory
    -0.33
    GOTREF
    -0.31
    íncia
    -0.31
    POSITIVE LOGITS
     nonUne
    0.55
    Ɓ
    0.54
    expandindo
    0.52
    irited
    0.49
    ienze
    0.49
    stateProvider
    0.49
    锈钢
    0.48
    RTHOOK
    0.48
    tedì
    0.47
    sidemargin
    0.47
    Act Density 0.011%

    No Known Activations