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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "back" in various contexts

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

    returning or resuming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserDao
    -0.40
     Knut
    -0.39
    SeekBar
    -0.37
    esi
    -0.35
    ly
    -0.35
    iola
    -0.32
    pdf
    -0.32
     would
    -0.32
    shtml
    -0.32
    Paraguay
    -0.31
    POSITIVE LOGITS
    Tikang
    0.70
    DockStyle
    0.67
    writeField
    0.61
     raiſ
    0.61
    featureID
    0.61
     PeEnEo
    0.60
     transfieras
    0.59
     wireType
    0.57
     autorytatywna
    0.57
     محفوظة
    0.56
    Act Density 0.009%

    No Known Activations