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

    Neuronpedia

    INDEX
    Explanations

    terms related to different contexts or modalities of operation and their significance

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

    on a basis or level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.50
     Houſe
    -0.49
    %@",
    -0.40
     Theſe
    -0.40
    '</
    -0.40
     Anſ
    -0.39
    %");
    -0.39
     houſe
    -0.38
    gjenge
    -0.37
     ruine
    -0.37
    POSITIVE LOGITS
    Javadoc
    0.59
     iż
    0.57
     viewDidLoad
    0.54
     laude
    0.53
    omitempty
    0.52
     للمعارف
    0.50
    ValueStyle
    0.50
    engkapnya
    0.50
     aspect
    0.50
    ContentAsync
    0.49
    Act Density 0.084%

    No Known Activations