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

    Neuronpedia

    INDEX
    Explanations

    references to the act of stripping or removal of elements or rights

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

    "strip" and image processing/removal functions

    np_acts-logits-general · gemini-2.0-flash

    strip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.50
     تضيفلها
    -0.47
    EndInit
    -0.46
     repr
    -0.46
     препратки
    -0.45
    ⋱
    -0.44
    VolleyError
    -0.44
     Family
    -0.43
    ReusableCell
    -0.43
     gr
    -0.43
    POSITIVE LOGITS
    strip
    1.40
     stripping
    1.38
     stripped
    1.31
     strip
    1.28
    Strip
    1.21
     Strip
    1.21
    stripped
    1.18
     STRIP
    1.16
     strips
    1.07
    STRIP
    1.07
    Act Density 0.375%

    No Known Activations