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

    Neuronpedia

    INDEX
    Explanations

    numbers and their structure in text

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

    URLs and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.56
     OFDb
    -0.53
    StateToProps
    -0.53
    ruitment
    -0.52
     виправивши
    -0.50
     IBOutlet
    -0.50
     صوتيه
    -0.49
    balleur
    -0.49
    <unused53>
    -0.48
    <unused68>
    -0.48
    POSITIVE LOGITS
    ://
    0.48
    /
    0.45
     /
    0.39
    SequentialGroup
    0.36
    TagMode
    0.36
     October
    0.36
     December
    0.35
     May
    0.35
     Day
    0.34
     June
    0.34
    Act Density 0.017%

    No Known Activations