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

    Neuronpedia

    INDEX
    Explanations

    sizes and volume

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bend
    -0.07
     contradict
    -0.06
     意
    -0.06
     possesses
    -0.06
     exped
    -0.06
     آس
    -0.06
    ids
    -0.06
     Ted
    -0.06
     pt
    -0.06
    .Messaging
    -0.06
    POSITIVE LOGITS
     нарез
    0.08
    .'<
    0.07
    lasyon
    0.07
     Buckley
    0.07
     khoán
    0.06
    =Value
    0.06
    ilder
    0.06
    }/#{
    0.06
     हर
    0.06
    "),"
    0.06
    Act Density 0.080%

    No Known Activations