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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "keep" in various contexts

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

    "keep"

    np_acts-logits-general · gemini-2.0-flash

    keep things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -1.02
    Personensuche
    -0.83
    ValueStyle
    -0.78
    OGND
    -0.73
    XmlAccessType
    -0.73
    homonymie
    -0.69
    Xna
    -0.65
     ModelRenderer
    -0.64
     actionMode
    -0.63
    saraba
    -0.63
    POSITIVE LOGITS
    Keeps
    1.08
     keep
    1.04
     KEEP
    1.02
    KEEP
    1.01
     Keep
    0.97
    keep
    0.96
     keeps
    0.94
    Keep
    0.94
     kept
    0.94
     Keeps
    0.90
    Act Density 0.038%

    No Known Activations