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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a novice or beginner status in various contexts

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

    new to or beginner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.49
     ब्रेकडाउन
    -0.47
    RTLU
    -0.45
    WriteTagHelper
    -0.45
    Viitteet
    -0.41
     avrebbero
    -0.40
     avrebbe
    -0.40
    rdquo
    -0.38
    LEncoder
    -0.38
     RISERVATA
    -0.38
    POSITIVE LOGITS
    Beginner
    0.63
     newbie
    0.62
     newbies
    0.59
     beginner
    0.58
     Beginner
    0.56
     newcomer
    0.53
     noob
    0.49
    新手
    0.48
     newcomers
    0.47
    noob
    0.47
    Act Density 0.009%

    No Known Activations