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

    Neuronpedia

    INDEX
    Explanations

    phrases related to directional movements and actions

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

    up out down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.90
     nahilalakip
    -0.84
     архивлан
    -0.84
    FunctionFlags
    -0.82
     виправивши
    -0.79
     وتسجيلات
    -0.76
    Архівовано
    -0.76
    IntoConstraints
    -0.75
     kasarigan
    -0.74
    writeFieldEnd
    -0.74
    POSITIVE LOGITS
    <eos>
    0.36
     of
    0.34
    Off
    0.33
     nhàng
    0.32
    Law
    0.32
    Flag
    0.32
     dàng
    0.32
    rån
    0.32
     the
    0.31
     Off
    0.31
    Act Density 0.061%

    No Known Activations