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

    Neuronpedia

    INDEX
    Explanations

    phrases related to addition or inclusion

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

    throw in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InitStruct
    -0.45
    :✨
    -0.44
     getNombre
    -0.40
    ViewImports
    -0.39
     berger
    -0.37
     archivo
    -0.37
     Mujeres
    -0.37
     CreateTagHelper
    -0.36
     betweenstory
    -0.36
    onore
    -0.35
    POSITIVE LOGITS
    astify
    0.50
    HtmlAttribute
    0.49
    再加上
    0.46
    sidemargin
    0.46
     NSCoder
    0.46
    hobia
    0.44
     CWE
    0.44
    AutoScaleMode
    0.43
     utafitiHapana
    0.43
    niz
    0.42
    Act Density 0.009%

    No Known Activations