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

    Neuronpedia

    INDEX
    Explanations

    phrases related to protective gear and safety precautions

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

    masks and protective gear

    np_acts-logits-general · gemini-2.0-flash

    face covering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DropColumn
    -0.60
    LabelTagHelper
    -0.55
    TagMode
    -0.54
     <>",
    -0.54
     незавершена
    -0.53
    脚注の使い方
    -0.53
    Билгалдахарш
    -0.52
     المعيارى
    -0.52
     Roskov
    -0.51
     calendriers
    -0.51
    POSITIVE LOGITS
     mask
    2.53
     masks
    2.40
     Mask
    2.20
    Mask
    2.14
    mask
    2.11
     Masks
    2.03
     MASK
    1.91
    Masks
    1.82
    masks
    1.81
     masking
    1.78
    Act Density 0.087%

    No Known Activations